ThinkQE: Query Expansion via an Evolving Thinking Process

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lei, Yibin, Shen, Tao, Yates, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914380361236480
author Lei, Yibin
Shen, Tao
Yates, Andrew
author_facet Lei, Yibin
Shen, Tao
Yates, Andrew
contents Effective query expansion for web search benefits from promoting both exploration and result diversity to capture multiple interpretations and facets of a query. While recent LLM-based methods have improved retrieval performance and demonstrate strong domain generalization without additional training, they often generate narrowly focused expansions that overlook these desiderata. We propose ThinkQE, a test-time query expansion framework addressing this limitation through two key components: a thinking-based expansion process that encourages deeper and comprehensive semantic exploration, and a corpus-interaction strategy that iteratively refines expansions using retrieval feedback from the corpus. Experiments on diverse web search benchmarks (DL19, DL20, and BRIGHT) show ThinkQE consistently outperforms prior approaches, including training-intensive dense retrievers and rerankers.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ThinkQE: Query Expansion via an Evolving Thinking Process
Lei, Yibin
Shen, Tao
Yates, Andrew
Information Retrieval
Computation and Language
Effective query expansion for web search benefits from promoting both exploration and result diversity to capture multiple interpretations and facets of a query. While recent LLM-based methods have improved retrieval performance and demonstrate strong domain generalization without additional training, they often generate narrowly focused expansions that overlook these desiderata. We propose ThinkQE, a test-time query expansion framework addressing this limitation through two key components: a thinking-based expansion process that encourages deeper and comprehensive semantic exploration, and a corpus-interaction strategy that iteratively refines expansions using retrieval feedback from the corpus. Experiments on diverse web search benchmarks (DL19, DL20, and BRIGHT) show ThinkQE consistently outperforms prior approaches, including training-intensive dense retrievers and rerankers.
title ThinkQE: Query Expansion via an Evolving Thinking Process
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2506.09260