@inproceedings{deng-etal-2025-silver,
    title = "A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression",
    author = "Deng, Chenlong  and
      Zhang, Zhisong  and
      Mao, Kelong  and
      Li, Shuaiyi  and
      Huang, Xinting  and
      Yu, Dong  and
      Dou, Zhicheng",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.241/",
    pages = "4861--4879",
    ISBN = "979-8-89176-251-0",
    abstract = "In this work, we provide an empirical investigation of gist-based context compression methods to improve context processing in large language models. We focus on two key questions: (1) How well can these methods replace full attention models? and (2) What potential failure patterns arise due to compression? Through extensive experiments, we show that while gist-based compression can achieve only slight performance loss on tasks like retrieval-augmented generation and long-document QA, it faces challenges in tasks like synthetic recall. Furthermore, we identify three key failure patterns: lost by the boundary, lost if surprise, and lost along the way. To mitigate these issues, we propose two effective strategies: fine-grained autoencoding, which enhances the reconstruction of original token information, and segment-wise token importance estimation, which adjusts optimization based on token dependencies. Our work provides valuable insights into the understanding of gist token-based context compression and offers practical strategies for improving compression capabilities."
}