@inproceedings{xue-etal-2026-deactivating,
    title = "Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment",
    author = "Xue, Zhiyu  and
      Qi, Zimo  and
      Liu, Guangliang  and
      Chen, Bocheng  and
      Pedarsani, Ramtin",
    editor = "Chang, Kai-Wei  and
      Mehrabi, Ninareh  and
      Krishna, Satyapriya  and
      Das, Anubrata  and
      Dhamala, Jwala  and
      Cao, Yang Trista  and
      Kumarage, Tharindu  and
      Ramakrishna, Anil  and
      Christodoulopoulos, Christos  and
      Wan, Yixin  and
      Galystan, Aram  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 6th Workshop on Trustworthy {NLP} ({T}rust{NLP} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.trustnlp-main.26/",
    pages = "402--412",
    ISBN = "979-8-89176-418-7"
}