@inproceedings{zhao-etal-2026-bias,
    title = "Bias Fitting to Mitigate Length Bias of Reward Model in {RLHF}",
    author = "Zhao, Kangwen  and
      Cai, Jianfeng  and
      Zhu, Jinhua  and
      Sun, Ruopei  and
      Xue, Dongyun  and
      Zhou, Wengang  and
      Li, Li  and
      Li, Houqiang",
    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.133/",
    pages = "2912--2927",
    ISBN = "979-8-89176-390-6"
}