@inproceedings{guo-etal-2024-attention,
    title = "Attention Score is not All You Need for Token Importance Indicator in {KV} Cache Reduction: Value Also Matters",
    author = "Guo, Zhiyu  and
      Kamigaito, Hidetaka  and
      Watanabe, Taro",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.emnlp-main.1178/",
    doi = "10.18653/v1/2024.emnlp-main.1178",
    pages = "21158--21166"
}