@inproceedings{hang-etal-2024-prior,
    title = "Prior Constraints-based Reward Model Training for Aligning Large Language Models",
    author = "Hang, Zhou  and
      Chenglong, Wang  and
      Yimin, Hu  and
      Tong, Xiao  and
      Chunliang, Zhang  and
      Jingbo, Zhu",
    editor = "Sun, Maosong  and
      Liang, Jiye  and
      Han, Xianpei  and
      Liu, Zhiyuan  and
      He, Yulan",
    booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
    month = jul,
    year = "2024",
    address = "Taiyuan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.ccl-1.107/",
    pages = "1395--1407",
    language = "eng"
}