Query2doc: Query Expansion with Large Language Models

2023/03/14 by Liang Wang, Nan Yang, Wang, Liang +3 · 24 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Topic Modeling #Web Data Mining and Analysis

paper · pdf · doi:10.48550/arxiv.2303.07678

openalex publication_date 2023/03/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems
• RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
• Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights
• PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework
• REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization
• Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval
• Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval
• DSEBench: A Test Collection for Explainable Dataset Search with Examples
• Rethinking On-policy Optimization for Query Augmentation
• LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval
• DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems
• Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
• Your Dense Retriever is Secretly an Expeditious Reasoner
• BloomIntent: Automating Search Evaluation with LLM-Generated Fine-Grained User Intents
• Enhancing Retrieval Augmentation via Adversarial Collaboration
• Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking
• LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge
• Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey
• Upcycling Candidate Tokens of Large Language Models for Query Expansion
• Question-to-Knowledge (Q2K): Multi-Agent Generation of Inspectable Facts for Product Mapping
• Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations
• CLAP: Coreference-Linked Augmentation for Passage Retrieval
• FinCPRG: A Bidirectional Generation Pipeline for Hierarchical Queries and Rich Relevance in Financial Chinese Passage Retrieval
• Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities

Related

• Exploring the Best Practices of Query Expansion with Large Language Models
• Query Expansion by Prompting Large Language Models
• Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey
• Corpus-Steered Query Expansion with Large Language Models
• ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance