{
 "id": "ScalerLab/JudgeBench",
 "owner": "ScalerLab",
 "name": "JudgeBench",
 "downloads": 2647,
 "likes": 12,
 "last_modified": "2024-10-09T18:10:45.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@misc{judgebench2024,\n  title={JudgeBench: A Benchmark for Evaluating LLM-Based Judges},\n  author={Sijun Tan and Siyuan Zhuang and Kyle Montgomery and Willian Yuan Tang and Alejandro Cuadron and Chenguang Wang and Raluca Ada Popa and Ion Stoica},\n  year={2024},\n  archivePrefix={arXiv},\n  url={https://arxiv.org/abs/2410.12784}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "57dd5e0b9817d07f05ec8f45a91b2ce1e310e308",
 "stated_evidence": "https://huggingface.co/datasets/ScalerLab/JudgeBench/blob/57dd5e0b9817d07f05ec8f45a91b2ce1e310e308/README.md",
 "file_evidence": "https://huggingface.co/datasets/ScalerLab/JudgeBench/tree/57dd5e0b9817d07f05ec8f45a91b2ce1e310e308",
 "card_nc": false
}