{
 "id": "Zhaoxuan/PUGC_data",
 "owner": "Zhaoxuan",
 "name": "PUGC_data",
 "downloads": 39,
 "likes": 0,
 "last_modified": "2025-10-17T16:10:17.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{tan-etal-2025-aligning,\n      title = \"Aligning Large Language Models with Implicit Preferences from User-Generated Content\",\n      author = \"Tan, Zhaoxuan  and\n        Li, Zheng  and\n        Liu, Tianyi  and\n        Wang, Haodong  and\n        Yun, Hyokun  and\n        Zeng, Ming  and\n        Chen, Pei  and\n        Zhang, Zhihan  and\n        Gao, Yifan  and\n        Wang, Ruijie  and\n        Nigam, Priyanka  and\n        Yin, Bing  and\n        Jiang, Meng\",\n      editor = \"Che, Wanxiang  and\n        Nabende, Joyce  and\n        Shutova, Ekaterina  and\n        Pilehvar, Mohammad Taher\",\n      booktitle = \"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n      month = jul,\n      year = \"2025\",\n      address = \"Vienna, Austria\",\n      publisher = \"Association for Computational Linguistics\",\n      url = \"https://aclanthology.org/2025.acl-long.384/\",\n      doi = \"10.18653/v1/2025.acl-long.384\",\n      pages = \"7792--7820\",\n      ISBN = \"979-8-89176-251-0\",\n      abstract = \"Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. In this work, we present PUGC, a novel framework that leverages implicit human Preferences in unlabeled User-Generated Content (UGC) to gen",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "11d95289f949987963ba237727059da41834e353",
 "stated_evidence": "https://huggingface.co/datasets/Zhaoxuan/PUGC_data/blob/11d95289f949987963ba237727059da41834e353/README.md",
 "file_evidence": "https://huggingface.co/datasets/Zhaoxuan/PUGC_data/tree/11d95289f949987963ba237727059da41834e353",
 "card_nc": false
}