@inproceedings{mao-etal-2026-models,
    title = "When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models",
    author = "Mao, Yingzhi  and
      Zhang, Chunkang  and
      Wang, Junxiang  and
      Guan, Xinyan  and
      Cao, Boxi  and
      Lu, Yaojie  and
      Lin, Hongyu  and
      Han, Xianpei  and
      Sun, Le",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1118/",
    pages = "22274--22302",
    ISBN = "979-8-89176-395-1"
}