@inproceedings{chen-etal-2024-improving-discriminative,
    title = "Improving Discriminative Capability of Reward Models in {RLHF} Using Contrastive Learning",
    author = "Chen, Lu  and
      Zheng, Rui  and
      Wang, Binghai  and
      Jin, Senjie  and
      Huang, Caishuang  and
      Ye, Junjie  and
      Zhang, Zhihao  and
      Zhou, Yuhao  and
      Xi, Zhiheng  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.852/",
    doi = "10.18653/v1/2024.emnlp-main.852",
    pages = "15270--15283"
}