@inproceedings{zhang-etal-2024-defending,
    title = "Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization",
    author = "Zhang, Zhexin  and
      Yang, Junxiao  and
      Ke, Pei  and
      Mi, Fei  and
      Wang, Hongning  and
      Huang, Minlie",
    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://preview.aclanthology.org/fix-sig-urls/2024.acl-long.481/",
    doi = "10.18653/v1/2024.acl-long.481",
    pages = "8865--8887"
}