Add arxiv paper link
Browse files
README.md
CHANGED
|
@@ -13,6 +13,7 @@ language:
|
|
| 13 |
|
| 14 |
**TokenHD** is a token-level hallucination detector trained on top of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) using the TokenHD pipeline. It assigns a hallucination probability to each token in an LLM-generated response, enabling fine-grained localization of errors without requiring predefined step segmentation.
|
| 15 |
|
|
|
|
| 16 |
Code: [github.com/rmin2000/TokenHD](https://github.com/rmin2000/TokenHD)
|
| 17 |
Training Data: [mr233/TokenHD-training-data](https://huggingface.co/datasets/mr233/TokenHD-training-data)
|
| 18 |
|
|
|
|
| 13 |
|
| 14 |
**TokenHD** is a token-level hallucination detector trained on top of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) using the TokenHD pipeline. It assigns a hallucination probability to each token in an LLM-generated response, enabling fine-grained localization of errors without requiring predefined step segmentation.
|
| 15 |
|
| 16 |
+
Paper: [arxiv.org/abs/2605.12384](https://arxiv.org/abs/2605.12384)
|
| 17 |
Code: [github.com/rmin2000/TokenHD](https://github.com/rmin2000/TokenHD)
|
| 18 |
Training Data: [mr233/TokenHD-training-data](https://huggingface.co/datasets/mr233/TokenHD-training-data)
|
| 19 |
|