{
 "id": "jaelly/MCJudgeBench",
 "owner": "jaelly",
 "name": "MCJudgeBench",
 "downloads": 78,
 "likes": 4,
 "last_modified": "2026-09-06T15:00:08.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{lee-etal-2026-mcjudgebench,\n    title = \"{MCJ}udge{B}ench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following\",\n    author = \"Lee, Jaeyun and Koh, Junyoung and Tok, Zeynel and Batra, Hunar and Clark, Ronald\",\n    booktitle = \"Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})\",\n    month = jul,\n    year = \"2026\",\n    address = \"San Diego, California, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.gem-main.23/\",\n    doi = \"10.18653/v1/2026.gem-main.23\",\n    pages = \"205--221\"\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "c64832efae480d3f1ed97ac3e877bc2162d9490d",
 "stated_evidence": "https://huggingface.co/datasets/jaelly/MCJudgeBench/blob/c64832efae480d3f1ed97ac3e877bc2162d9490d/README.md",
 "file_evidence": "https://huggingface.co/datasets/jaelly/MCJudgeBench/tree/c64832efae480d3f1ed97ac3e877bc2162d9490d",
 "card_nc": false
}