@inproceedings{wang-etal-2026-outcome,
    title = "Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models",
    author = "Wang, Binghai  and
      Liu, Yantao  and
      Liu, Yuxuan  and
      Tang, Tianyi  and
      Wang, Shenzhi  and
      Gao, Chang  and
      Zheng, Chujie  and
      Zhang, Yichang  and
      Yu, Le  and
      Liu, Shixuan  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing  and
      Yu, Bowen  and
      Huang, Fei  and
      Lin, Junyang",
    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.1924/",
    pages = "41482--41508",
    ISBN = "979-8-89176-390-6"
}