@inproceedings{liu-etal-2024-intactkv,
    title = "{I}ntact{KV}: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact",
    author = "Liu, Ruikang  and
      Bai, Haoli  and
      Lin, Haokun  and
      Li, Yuening  and
      Gao, Han  and
      Xu, Zhengzhuo  and
      Hou, Lu  and
      Yao, Jun  and
      Yuan, Chun",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-acl.460/",
    doi = "10.18653/v1/2024.findings-acl.460",
    pages = "7716--7741"
}