@inproceedings{zhangyin-etal-2024-qian,
    title = "浅谈大模型时代下的检索增强:发展趋势、挑战与展望(Enhancing Large Language Models with Retrieval-Augmented Techniques: Trends, Challenges, and Prospects)",
    author = "Zhangyin, Feng  and
      Kun, Zhu  and
      Weitao, Ma  and
      Lei, Huang  and
      Bing, Qin  and
      Ting, Liu  and
      Xiaocheng, Feng",
    editor = "Zhao, Xin",
    booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 2: Frontier Forum)",
    month = jul,
    year = "2024",
    address = "Taiyuan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.ccl-2.9/",
    pages = "151--168",
    language = "zho",
    abstract = "``大型语言模型(LLM) 在各种自然语言任务上表现出了卓越的性能,但它们很容易受到过时数据和特定领域限制的影响。为了应对这些挑战,研究人员整合不同来源的外部信息来增强大语言模型,具体方法如检索增强等。在本文中,我们综合讨论了检索增强技术的发展趋势,包括检索时机规划、检索技术、以及检索结果的利用。此外,我们介绍了当前可用于检索增强任务的数据集和评价方法,并指出了应用和潜在研究方向。我们希望这项综述能够为社区提供对该研究领域的快速了解和全面概述,以启发未来的研究工作。''"
}