@inproceedings{zhou-etal-2024-large-language,
    title = "Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks",
    author = "Zhou, Yue  and
      Zou, Henry Peng  and
      Di Eugenio, Barbara  and
      Zhang, Yang",
    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://aclanthology.org/2024.emnlp-main.738/",
    doi = "10.18653/v1/2024.emnlp-main.738",
    pages = "13293--13304"
}