@inproceedings{ramesh-etal-2024-gpt,
    title = "{GPT}-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation",
    author = "Ramesh, Govind  and
      Dou, Yao  and
      Xu, Wei",
    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.1235/",
    doi = "10.18653/v1/2024.emnlp-main.1235",
    pages = "22139--22148"
}