Query2doc: Query Expansion with Large Language Models

被引:0
|
作者
Wang, Liang [1 ]
Yang, Nan [1 ]
Wei, Furu [1 ]
机构
[1] Microsoft Res, Beijing, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language models (LLMs), and then expands the query with generated pseudo-documents. LLMs are trained on web-scale text corpora and are adept at knowledge memorization. The pseudo-documents from LLMs often contain highly relevant information that can aid in query disambiguation and guide the retrievers. Experimental results demonstrate that query2doc boosts the performance of BM25 by 3% to 15% on ad-hoc IR datasets, such as MS-MARCO and TREC DL, without any model fine-tuning. Furthermore, our method also benefits state-of-the-art dense retrievers in terms of both in-domain and out-of-domain results.
引用
收藏
页码:9414 / 9423
页数:10
相关论文
共 50 条
  • [41] Advanced Agricultural Query Resolution Using Ensemble-Based Large Language Models
    Dofitas Jr, Cyreneo
    Kim, Yong-Woon
    Byun, Yung-Cheol
    IEEE ACCESS, 2025, 13 : 34732 - 34746
  • [42] Context-Driven Interactive Query Simulations Based on Generative Large Language Models
    Engelmann, Bjoern
    Breuer, Timo
    Friese, Jana Isabelle
    Schaer, Philipp
    Fuhr, Norbert
    ADVANCES IN INFORMATION RETRIEVAL, ECIR 2024, PT II, 2024, 14609 : 173 - 188
  • [43] Query Generation Using Large Language Models A Reproducibility Study of Unsupervised Passage Reranking
    Rau, David
    Kamps, Jaap
    ADVANCES IN INFORMATION RETRIEVAL, ECIR 2024, PT IV, 2024, 14611 : 226 - 239
  • [44] Query models
    Stein, D
    Hanenberg, S
    Unland, R
    UML 2004 - THE UNIFIED MODELING LANGUAGE: MODELING LANGUAGES AND APPLICATIONS, PROCEEDINGS, 2004, 3273 : 98 - 112
  • [45] Query Expansion for Personalized Cross-Language Information Retrieval
    Zhou, Dong
    Lawless, Seamus
    Liu, Jianxun
    Zhang, Sanrong
    Xu, Yu
    10TH INTERNATIONAL WORKSHOP ON SEMANTIC AND SOCIAL MEDIA ADAPTATION AND PERSONALIZATION SMAP 2015, 2015, : 18 - 22
  • [46] Application of Recursive Query on Structured Query Language Server
    荀雪莲
    ABHIJIT Sen
    姚志强
    JournalofDonghuaUniversity(EnglishEdition), 2023, 40 (01) : 68 - 73
  • [47] A Trace Query Language for Rule-Based Models
    Laurent, Jonathan
    Medina-Abarca, Hector F.
    Boutillier, Pierre
    Yang, Jean
    Fontana, Walter
    COMPUTATIONAL METHODS IN SYSTEMS BIOLOGY (CMSB 2018), 2018, 11095 : 220 - 237
  • [48] SELECTSCRIPT: A Query Language for Robotic World Models and Simulations
    Dietrich, Andre
    Zug, Sebastian
    Kaiser, Joerg
    2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2015, : 6254 - 6260
  • [49] BIMQL - An open query language for building information models
    Mazairac, Wiet
    Beetz, Jakob
    ADVANCED ENGINEERING INFORMATICS, 2013, 27 (04) : 444 - 456
  • [50] Multimedia object query language and its query processing
    Fudan Univ, Shanghai, China
    Ruan Jian Xue Bao, 7 (694-701):