@inproceedings{long-etal-2026-safety,
    title = "When Safety Alignment Fails to Generalize: Probing with Language Game Jailbreaks",
    author = "Long, Zewen  and
      Peng, Yu  and
      Dong, Fangming  and
      Li, Congyi  and
      Guan, Xingmao  and
      Wu, Shu  and
      Chen, Kai",
    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.739/",
    pages = "15020--15037",
    ISBN = "979-8-89176-395-1"
}