# Exploring the Best Practices of Query Expansion with Large Language Models

arXiv: https://arxiv.org/abs/2401.06311 · HTML: https://mlsanity.com/paper/2401.06311/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2024.

## Built on by (most cited first, 17 of 17)

- [REARANK: Reasoning Re-ranking Agent via Reinforcement Learning](https://mlsanity.com/paper/2505.20046/) (2025)
- [Recursive Self-Evolving Agents via Held-Out Selection](https://mlsanity.com/paper/2606.28374/) (2026)
- [QueryGym: A Toolkit for Reproducible LLM-Based Query Reformulation](https://mlsanity.com/paper/2511.15996/) (2025)
- [Aligning Extraction and Generation for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.04789/) (2025)
- [A Reproducibility Study of LLM-Based Query Reformulation](https://mlsanity.com/paper/2604.27421/) (2026)
- [A Survey of Query Optimization in Large Language Models](https://mlsanity.com/paper/2412.17558/) (2024)
- [ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models](https://mlsanity.com/paper/2511.00489/) (2025)
- [Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks](https://mlsanity.com/paper/2602.06526/) (2026)
- [ReFormeR: Learning and Applying Explicit Query Reformulation Patterns](https://mlsanity.com/paper/2604.01417/) (2026)
- [Rethinking RAG in Long Videos: What to Retrieve and How to Use It?](https://mlsanity.com/paper/2606.13141/) (2026)
- [Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability](https://mlsanity.com/paper/2608.11238/) (2026)
- [Generative Query Expansion with Multilingual LLMs for Cross-Lingual Information Retrieval](https://mlsanity.com/paper/2511.19325/) (2025)
- [RAG without Forgetting: Continual Query-Infused Key Memory](https://mlsanity.com/paper/2602.05152/) (2026)
- [Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion](https://mlsanity.com/paper/2602.08917/) (2026)
- [AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation](https://mlsanity.com/paper/2603.19710/) (2026)
- [Generated Query Expansion Still Helps Strong Sparse Retrieval: A Controlled Study with SPLADE-v3](https://mlsanity.com/paper/2609.37911/) (2026)
- [Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion](https://mlsanity.com/paper/2610.13810/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are foundational in language technologies, particularly in information retrieval (IR). Previous studies have utilized LLMs for query expansion, achieving notable improvements in IR. In this paper, we thoroughly explore the best practice of leveraging LLMs for query expansion. To this end, we introduce a training-free, straightforward yet effective framework called Multi-Text Generation Integration (textscMuGI). It leverages LLMs to generate multiple pseudo-references, integrating them with queries to enhance both sparse and dense retrievers. Our empirical findings reveal that: (1) Increasing the number of samples from LLMs benefits IR systems; (2) A balance between the query and pseudo-documents, and an effective integration strategy, is critical for high performance; (3) Contextual information from LLMs is essential, even boost a 23M model to outperform a 7B baseline model; (4) Pseudo relevance feedback can further calibrate queries for improved performance; and (5) Query expansion is widely applicable and versatile, consistently enhancing models ranging from 23M to 7B parameters. Our code and all generated references are made available at urlhttps://github.com/lezhang7/RetrievalMuGI