@inproceedings{luo-etal-2025-dynamic,
    title = "Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models",
    author = "Luo, Weidi  and
      Cao, He  and
      Liu, Zijing  and
      Wang, Yu  and
      Wong, Aidan  and
      Feng, Bin  and
      Yao, Yuan  and
      Li, Yu",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-naacl.368/",
    pages = "6599--6620",
    ISBN = "979-8-89176-195-7",
    abstract = "With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly in domain-specific scenarios like chemistry, where a lack of specialized knowledge can lead to the generation of harmful responses to malicious queries. (ii) over-defensiveness, which compromises the general utility and responsiveness of LLMs. To mitigate these issues, we introduce a multi-agents-based defense framework, Guide for Defense (G4D), which leverages accurate external information to provide an unbiased summary of user intentions and analytically grounded safety response guidance. Extensive experiments on popular jailbreak attacks and benign datasets show that our G4D can enhance LLM{'}s robustness against jailbreak attacks on general and domain-specific scenarios without compromising the model{'}s general functionality."
}