@inproceedings{zhou-etal-2024-alignment,
    title = "How Alignment and Jailbreak Work: Explain {LLM} Safety through Intermediate Hidden States",
    author = "Zhou, Zhenhong  and
      Yu, Haiyang  and
      Zhang, Xinghua  and
      Xu, Rongwu  and
      Huang, Fei  and
      Li, Yongbin",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.139/",
    doi = "10.18653/v1/2024.findings-emnlp.139",
    pages = "2461--2488"
}