@inproceedings{li-etal-2025-multilingual-collaborative,
    title = "Multilingual Collaborative Defense for Large Language Models",
    author = "Li, Hongliang  and
      Xu, Jinan  and
      Cui, Gengping  and
      Guan, Changhao  and
      Mo, Fengran  and
      Huang, Kaiyu",
    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/name-variant-enfa-fane/2025.findings-emnlp.200/",
    doi = "10.18653/v1/2025.findings-emnlp.200",
    pages = "3735--3755",
    ISBN = "979-8-89176-335-7",
    abstract = "The robustness and security of Large Language Models (LLMs) face increasing threats, especially in multilingual settings. A notable vulnerability is ``jailbreaking'' via translating harmful queries into rare or underrepresented languages, which often bypasses existing safeguards. In this work, we propose Multilingual Collaborative Defense (MCD), a novel learning method that optimizes a continuous soft safety prompt automatically to facilitate multilingual safeguarding of LLMs. MCD organically leverages collaborative signals from multiple languages by rotating each as the training ``center,'' allowing auxiliary languages to reinforce safety prompt learning and ensuring cross{-}lingual consistency. As a result, MCD improves defense performance across all languages, reduces false refusals, and mitigates safety misalignment caused by corpus imbalance. To evaluate MCD, we construct multilingual versions of jailbreak benchmarks such as MaliciousInstruct and AdvBench, including zero-shot languages, to assess language transferability. Experiments show that MCD outperforms prior approaches in multilingual jailbreak defense while exhibiting strong cross-lingual generalization. Our code is available at https://github.com/HLiang-Lee/MCD."
}