@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",
    abstract = "Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail to fully leverage LLMs' internal cognitive processes. Inspired by humans' reflective thinking capability, we first show that LLMs can similarly perform internal assessments about safety in their internal states. Building on this insight, we propose **SafeSwitch**, a dynamic framework that regulates unsafe outputs by utilizing the prober-based internal state monitor that actively detects harmful intentions, and activates a safety head that leads to safer and more conservative responses only when necessary. SafeSwitch reduces harmful outputs by approximately 80{\%} on harmful queries while maintaining strong utility, reaching a Pareto optimal among several methods. Our method is also advantageous over traditional methods in offering more informative, context-aware refusals, and achieves these benefits while only tuning less than 6{\%} of the original parameters. SafeSwitch demonstrates large language models' capacity for self-awareness and reflection regarding safety, offering a promising approach to more nuanced and effective safety controls."
}