@inproceedings{zhou-etal-2025-llmxmapreduce,
    title = "{LLM}$\times${M}ap{R}educe: Simplified Long-Sequence Processing using Large Language Models",
    author = "Zhou, Zihan  and
      Li, Chong  and
      Chen, Xinyi  and
      Wang, Shuo  and
      Chao, Yu  and
      Li, Zhili  and
      Wang, Haoyu  and
      Shi, Qi  and
      Tan, Zhixing  and
      Han, Xu  and
      Shi, Xiaodong  and
      Liu, Zhiyuan  and
      Sun, Maosong",
    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.1341/",
    pages = "27664--27678",
    ISBN = "979-8-89176-251-0",
    abstract = "We propose a training-free framework that enables large language models (LLMs) to effectively process long texts, using a divide-and-conquer strategy for comprehensive document understanding.The proposed LLM$\times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate outputs to produce the final response. The main challenge for divide-and-conquer long text processing frameworks lies in the risk of losing essential long-range information due to document splitting, which can lead the model to produce incomplete or incorrect answers based on the segmented texts.Disrupted long-range information can be classified into two categories: inter-chunk dependency and inter-chunk conflict.We design a structured information protocol to better cope with inter-chunk dependency and an in-context confidence calibration mechanism to resolve inter-chunk conflicts. Experiments demonstrate that LLM$\times$MapReduce outperforms representative open-source and commercial long-context LLMs and is compatible with several models.Our framework can also function as a data synthesis engine, capable of generating high-quality long-alignment data using only short-context LLMs."
}