@inproceedings{zhang-etal-2026-selfgrader,
    title = "{S}elf{G}rader: {LLM} Jailbreak Detection via Anchored Token-Level Logits",
    author = "Zhang, Zikai  and
      Hu, Rui  and
      Kotevska, Olivera  and
      Xu, Jiahao",
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-aacl.27/",
    pages = "493--523",
    ISBN = "979-8-89176-444-6"
}