{
  "id": "wildreward2026",
  "type": "paper-conference",
  "title": "WildReward: Learning Reward Models from In-the-Wild Human Interactions",
  "author": [{"given":"Hao","family":"Peng"},{"given":"Yunjia","family":"Qi"},{"given":"Xiaozhi","family":"Wang"},{"given":"Zijun","family":"Yao"},{"given":"Lei","family":"Hou"},{"given":"Juanzi","family":"Li"}],
  "issued": {"date-parts":[[2026]]},
  "URL": "https://aclanthology.org/2026.acl-long.864/",
  "container-title": "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
  "DOI": "10.18653/v1/2026.acl-long.864",
  "publisher": "Association for Computational Linguistics",
  "page": "18932–18948",
  "custom": {
    "record_url": "https://yuntiandeng.com/wildchat/papers/wildreward/",
    "first_public_date": "2026-02-09",
    "first_arxiv_submission": "2026-02-09",
    "citation_note": "ACL 2026 proceedings paper."
  }
}