@inproceedings{lu-etal-2025-chain,
    title = "Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?",
    author = "Lu, Chengda  and
      Fan, Xiaoyu  and
      Huang, Yu  and
      Xu, Rongwu  and
      Li, Jijie  and
      Xu, Wei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.339/",
    doi = "10.18653/v1/2025.findings-acl.339",
    pages = "6523--6546",
    ISBN = "979-8-89176-256-5",
    abstract = "Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns. In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking? Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness. Based on the theoretical insights, we propose a novel jailbreak method, FicDetail, whose practical performance validates our theoretical findings."
}