@inproceedings{liang-etal-2026-dual,
    title = "{DUAL} {RM}: Beyond Rule-based Preference Reward Modeling via Meta-Reward",
    author = "Liang, Xiaobo  and
      Wang, Wanfu  and
      Huang, Qipeng  and
      Ding, Yuyang  and
      Tang, Zecheng  and
      Ji, Yixin  and
      Chen, Qianben  and
      Zhao, Zhe  and
      Chen, Kehai  and
      Li, Juntao  and
      Zhang, Min",
    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.1729/",
    pages = "37281--37296",
    ISBN = "979-8-89176-390-6"
}