Skip to content
/ cs_bot Public

The automatic system update the information of survey everyday on readme.

0 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

shintaro-ozaki/cs_bot

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

288 Commits
.github/workflows
.github/workflows
 
 
README.md
README.md
 
 
arxiv_survey.py
arxiv_survey.py
 
 

Repository files navigation

Survey


http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v2 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2403.14112v2 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .
http://arxiv.org/abs/2407.15281v1 SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.
http://arxiv.org/abs/2304.11164v1 Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for commonsense reasoning, we explore an alternative dialectical evaluation. The goal of this kind of evaluation is not to obtain an aggregate performance value but to find failures and map the boundaries of the system. Dialoguing with the system gives the opportunity to check for consistency and get more reassurance of these boundaries beyond anecdotal evidence. In this paper we conduct some qualitative investigations of this kind of evaluation for the particular case of spatial reasoning (which is a fundamental aspect of commonsense reasoning). We conclude with some suggestions for future work both to improve the capabilities of language models and to systematise this kind of dialectical evaluation.
http://arxiv.org/abs/2410.14897v1 From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.
http://arxiv.org/abs/2402.17302v3 Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotators, resulting in ~4.5K questions per language (~9K in total), making our dataset the largest of its kind. Our experiments show that automatic data adaptation from an existing English dataset is less effective for Sundanese. Interestingly, using the direct generation method on the target language, GPT-4 Turbo can generate questions with adequate general knowledge in both languages, albeit not as culturally 'deep' as humans. We also observe a higher occurrence of fluency errors in the Sundanese dataset, highlighting the discrepancy between medium- and lower-resource languages.
http://arxiv.org/abs/2410.23844v1 Commonsense Knowledge Editing Based on Free-Text in LLMs Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real world, characterized by broad knowledge scope, long content and non instantiation. The editing objects of previous methods (e.g., MEMIT) were single token or entity, which were not suitable for commonsense knowledge in free-text form. To address the aforementioned challenges, we conducted experiments from two perspectives: knowledge localization and knowledge editing. Firstly, we introduced Knowledge Localization for Free-Text(KLFT) method, revealing the challenges associated with the distribution of commonsense knowledge in MLP and Attention layers, as well as in decentralized distribution. Next, we propose a Dynamics-aware Editing Method(DEM), which utilizes a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge, and uses Knowledge Editing Module to update knowledge. The DEM method fully explores the potential of the MLP and Attention layers, and successfully edits commonsense knowledge based on free-text. The experimental results indicate that the DEM can achieve excellent editing performance.
http://arxiv.org/abs/2403.14112v3 Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .

About

The automatic system update the information of survey everyday on readme.

Resources

Readme
Activity

Stars

0 stars

Watchers

1 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages