Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Query2doc: Query Expansion with Large Language Models

About

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.

Liang Wang, Nan Yang, Furu Wei• 2023

Related benchmarks

TaskDatasetResultRank
Multi-hop Question Answering2WikiMultihopQA
EM38
278
Multi-hop Question AnsweringHotpotQA
F1 Score67.65
221
Multi-hop Question AnsweringMuSiQue
EM22
106
Information RetrievalBEIR v1.0.0 (test)--
55
Tool CallingAPI-Bank L-1--
46
Medical Question AnsweringMedical QA Evaluation Suite (MedQA, MedMCQA, MMLU-Med, PubMedQA, BioASQ, SEER, DDXPlus, MIMIC-IV)
MedQA Score62.92
27
Question AnsweringNaturalQA
EM36.87
26
RetrievalBridge (test)
Hit@1071
25
Tool CallingAPI-Bank L-2--
25
Question AnsweringWebQA
EM26.03
23
Showing 10 of 35 rows

Other info

Follow for update