@inproceedings{zhang-etal-2024-prototypical,
    title = "Prototypical Reward Network for Data-Efficient RLHF",
    author = "Zhang, Jinghan  and
      Wang, Xiting  and
      Jin, Yiqiao  and
      Chen, Changyu  and
      Zhang, Xinhao  and
      Liu, Kunpeng",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.748/",
    doi = "10.18653/v1/2024.acl-long.748",
    pages = "13871--13884"
}