{
 "id": "llm-agents/CriticBench",
 "owner": "llm-agents",
 "name": "CriticBench",
 "downloads": 424,
 "likes": 22,
 "last_modified": "2024-02-23T12:57:09.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering",
  "text-classification",
  "text-generation"
 ],
 "citation": "@misc{lin2024criticbench,\n    title={CriticBench: Benchmarking LLMs for Critique-Correct Reasoning}, \n    author={Zicheng Lin and Zhibin Gou and Tian Liang and Ruilin Luo and Haowei Liu and Yujiu Yang},\n    year={2024},\n    eprint={2402.14809},\n    archivePrefix={arXiv},\n    primaryClass={cs.CL}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "b96a766ac74020e2403a86fa0e92260c0e28bfdb",
 "stated_evidence": "https://huggingface.co/datasets/llm-agents/CriticBench/blob/b96a766ac74020e2403a86fa0e92260c0e28bfdb/README.md",
 "file_evidence": "https://huggingface.co/datasets/llm-agents/CriticBench/tree/b96a766ac74020e2403a86fa0e92260c0e28bfdb",
 "card_nc": false
}