A Reproducibility Study of LLM-Based Query Reformulation

TL;DR

This study systematically evaluates the reproducibility of LLM-based query reformulation methods across diverse settings, revealing stability issues and the importance of retrieval paradigms, and provides an open toolkit for ongoing comparison.

Contribution

It offers a unified experimental framework for reproducibility, compares multiple LLM-based reformulation methods, and releases an open-source toolkit with a public leaderboard.

Findings

Reformulation gains depend heavily on the retrieval paradigm.

Improvements in lexical retrieval do not always transfer to neural retrievers.

Larger LLMs do not always improve downstream performance.

Abstract

Large Language Models (LLMs) are now widely used for query reformulation and expansion in Information Retrieval, with many studies reporting substantial effectiveness gains. However, these results are typically obtained under heterogeneous experimental conditions, making it difficult to assess which findings are reproducible and which depend on specific implementation choices. In this work, we present a systematic reproducibility and comparative study of ten representative LLM-based query reformulation methods under a unified and strictly controlled experimental framework. We evaluate methods across two architectural LLM families at two parameter scales, three retrieval paradigms (lexical, learned sparse, and dense), and nine benchmark datasets spanning TREC Deep Learning and BEIR. Our results show that reformulation gains are strongly conditioned on the retrieval paradigm, that improvements observed under lexical retrieval do not consistently transfer to neural retrievers, and that larger LLMs do not uniformly yield better downstream performance. These findings clarify the stability and limits of reported gains in prior work. To enable transparent replication and ongoing comparison, we release all prompts, configurations, evaluation scripts, and run files through QueryGym, an open-source reformulation toolkit with a public leaderboard.\footnote{https://leaderboard.querygym.com}