@inproceedings{qiyuan-etal-2025-efficient,
    title = "Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling",
    author = "Qiyuan, Deng  and
      Bai, Xuefeng  and
      Chen, Kehai  and
      Wang, Yaowei  and
      Nie, Liqiang  and
      Zhang, Min",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.1504/",
    pages = "31156--31171",
    ISBN = "979-8-89176-251-0"
}