@inproceedings{huang-etal-2026-mask,
    title = "Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient d{LLM} Inference",
    author = "Huang, Jianuo  and
      Zhang, Yaojie  and
      Yang, Yicun  and
      Huang, Benhao  and
      Zhang, Linfeng",
    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.170/",
    pages = "3456--3479",
    ISBN = "979-8-89176-395-1"
}