diff --git a/tutorials/text/README.md b/tutorials/text/README.md
index 6e2bb8ed99..bbe7b3e3f2 100644
--- a/tutorials/text/README.md
+++ b/tutorials/text/README.md
@@ -11,11 +11,13 @@ Hands-on tutorials for curating text data with NeMo Curator. Complete working ex
 | Tutorial | Description | Files |
 |----------|-------------|-------|
 | **[Download & Extract](download-and-extract/)** | Data acquisition workflows | `download_extract_tutorial.ipynb` |
-| **[Deduplication](deduplication/)** | Remove duplicate content | `semantic_e2e.ipynb`, `semantic_step_by_step.ipynb` |
-| **[Classification](distributed-data-classification/)** | Quality assessment and categorization | `quality-classification.ipynb`, `domain-classification.ipynb`, `aegis-classification.ipynb`, `fineweb-edu-classification.ipynb` |
+| **[Deduplication](deduplication/)** | Remove duplicate content | Fuzzy and semantic deduplication notebooks |
+| **[Classification](distributed-data-classification/)** | Quality assessment and categorization | `quality-classification.ipynb`, `domain-classification.ipynb`, `fineweb-edu-classification.ipynb`, and more |
 | **[PEFT Curation](peft-curation/)** | Instruction-tuning data preparation | `main.py`, `stages.py` |
 | **[TinyStories](tinystories/)** | End-to-end processing pipeline | `main.py`, `stages.py` |
 | **[Megatron Tokenizing](megatron-tokenizer/)** | Tokenization pipeline that produces Megatron-LM ready files | `main.py` |
+| **[Llama Nemotron Data Curation](llama-nemotron-data-curation/)** | Data curation on the Llama Nemotron Post-Training Dataset | `main.py` and helper files |
+| **[GLiNER-based PII Redaction](gliner-pii-redaction/)** | Redacting personally identifiable information with NVIDIA's GLiNER-PII model | `gliner_pii_redaction.ipynb` |
 
 ## Documentation Links
 
diff --git a/tutorials/text/gliner-pii-redaction/README.md b/tutorials/text/gliner-pii-redaction/README.md
index 7a01603c1a..b329beeef4 100644
--- a/tutorials/text/gliner-pii-redaction/README.md
+++ b/tutorials/text/gliner-pii-redaction/README.md
@@ -13,3 +13,5 @@ Additionally, the tutorial uses the [GLiNER](https://github.com/urchade/GLiNER)
 ```bash
 uv pip install gliner
 ```
+
+For reference, this tutorial was tested with `gliner==0.2.24`.
diff --git a/tutorials/text/gliner-pii-redaction/gliner_pii_redaction.ipynb b/tutorials/text/gliner-pii-redaction/gliner_pii_redaction.ipynb
index 7c993f55df..2d551b70f5 100644
--- a/tutorials/text/gliner-pii-redaction/gliner_pii_redaction.ipynb
+++ b/tutorials/text/gliner-pii-redaction/gliner_pii_redaction.ipynb
@@ -26,6 +26,13 @@
     "# !uv pip install gliner"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For reference, this tutorial was tested with `gliner==0.2.24`."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
diff --git a/tutorials/text/gliner-pii-redaction/gliner_pii_redactor.py b/tutorials/text/gliner-pii-redaction/gliner_pii_redactor.py
index 32fe3bf547..2274381897 100644
--- a/tutorials/text/gliner-pii-redaction/gliner_pii_redactor.py
+++ b/tutorials/text/gliner-pii-redaction/gliner_pii_redactor.py
@@ -164,7 +164,7 @@ def process(self, batch: DocumentBatch) -> DocumentBatch | None:
 
         # Run model inference via the GLiNER library
         # This returns a list of dictionaries per document, each containing the entities and their confidence scores
-        entities = self.model.run(
+        entities = self.model.inference(
             df[self.text_field].tolist(),
             self.labels,
             threshold=self.threshold,