@inproceedings{qin-etal-2026-reflectrm,
    title = "{R}eflect{RM}: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework",
    author = "Qin, Kai  and
      Liu, Liangxin  and
      Liang, Yu  and
      Wang, Longzheng  and
      Wangyan  and
      Yueyang, Zhang  and
      Xia, Long  and
      Sun, Zhiyuan  and
      Liu, Houde  and
      Shi, Daiting",
    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.1676/",
    pages = "36207--36223",
    ISBN = "979-8-89176-390-6"
}