@inproceedings{zhang-etal-2025-tokens,
    title = "More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in {KV} Cache Compression",
    author = "Zhang, Jiebin  and
      Zhu, Dawei  and
      Song, Yifan  and
      Wu, Wenhao  and
      Kuang, Chuqiao  and
      Li, Xiaoguang  and
      Shang, Lifeng  and
      Liu, Qun  and
      Li, Sujian",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.429/",
    pages = "8092--8105",
    ISBN = "979-8-89176-335-7"
}