@inproceedings{peng-etal-2026-wildreward,
    title = "{W}ild{R}eward: Learning Reward Models from In-the-Wild Human Interactions",
    author = "Peng, Hao  and
      Qi, Yunjia  and
      Wang, Xiaozhi  and
      Yao, Zijun  and
      Hou, Lei  and
      Li, Juanzi",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.864/",
    pages = "18932--18948",
    ISBN = "979-8-89176-390-6"
}