EMNLP 2024main1 citations

SEGMENT+: Long Text Processing with Short-Context Language Models

Wei Shi, Shuang Li, Kerun Yu, Jinglei Chen, Zujie Liang, Xinhui Wu, Yuxi Qian, Feng Wei

Abstract

There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-input processing tasks, such as understanding extensive documents and extracting detailed information from lengthy and noisy data. In response, we introduce Segment+, a general framework that enables LMs to handle extended inputs within limited context windows efficiently. Segment+ utilizes structured notes and a filtering module to manage information flow, resulting in a system that is both controllable and interpretable. Our extensive experiments across various model sizes, focusing on long-document question-answering and Needle-in-a-Haystack tasks, demonstrate the effectiveness of Segment+ in improving performance.

BibTeX
@inproceedings{shi-etal-2024-segment,
    title = "{SEGMENT}+: Long Text Processing with Short-Context Language Models",
    author = "Shi, Wei  and
      Li, Shuang  and
      Yu, Kerun  and
      Chen, Jinglei  and
      Liang, Zujie  and
      Wu, Xinhui  and
      Qian, Yuxi  and
      Wei, Feng  and
      Zheng, Bo  and
      Liang, Jiaqing  and
      Chen, Jiangjie  and
      Xiao, Yanghua",
    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://aclanthology.org/2024.emnlp-main.926/",
    doi = "10.18653/v1/2024.emnlp-main.926",
    pages = "16605--16617"
}
SEGMENT+: Long Text Processing with Short-Context Language Models · EMNLP 2024