@inproceedings{han-etal-2025-safeswitch,
    title = "{S}afe{S}witch: Steering Unsafe {LLM} Behavior via Internal Activation Signals",
    author = "Han, Peixuan  and
      Qian, Cheng  and
      Chen, Xiusi  and
      Zhang, Yuji  and
      Ji, Heng  and
      Zhang, Denghui",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.366/",
    doi = "10.18653/v1/2025.findings-emnlp.366",
    pages = "6936--6955",
    ISBN = "979-8-89176-335-7"
}