The "LLM-Detection-Challenge" invites participants to develop a machine learning model capable of distinguishing between essays written by middle and high school students and those generated by large language models (LLMs). This competition aims to address the growing concerns in the academic community regarding the potential misuse of LLMs for plagiarism and the impact on student learning.
- Dataset: A diverse mix of student-written essays and essays generated by various LLMs.
- Goal: To advance the state of the art in LLM text detection and help maintain academic integrity.
- Organizers: Vanderbilt University and The Learning Agency Lab, in collaboration with Kaggle.
- Start Date: [Oct 31 2023]
- End Date: /
Interested participants can join the competition on the Kaggle platform. Guidelines for entry and data access will be provided upon registration.
Contributions from the academic and research community are highly encouraged. Prospective contributors are requested to peruse our contribution guidelines prior to the submission of any pull requests.
In alignment with our commitment to open-source research and transparency, this project adheres to the GNU General Public License v3.0. Detailed terms and conditions are available in the LICENSE file.
For further inquiries or detailed discussion, please reach out to the owner of this repos.