@inproceedings{zhan-etal-2024-removing,
    title = "Removing {RLHF} Protections in {GPT}-4 via Fine-Tuning",
    author = "Zhan, Qiusi  and
      Fang, Richard  and
      Bindu, Rohan  and
      Gupta, Akul  and
      Hashimoto, Tatsunori  and
      Kang, Daniel",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-short.59/",
    doi = "10.18653/v1/2024.naacl-short.59",
    pages = "681--687"
}