# LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queries

arXiv: https://arxiv.org/abs/2505.12694 · HTML: https://mlsanity.com/paper/2505.12694/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2025.

## Built on by (most cited first, 10 of 10)

- [Powering Job Search at Scale: LLM-Enhanced Query Understanding in Job Matching Systems](https://mlsanity.com/paper/2509.09690/) (2025)
- [Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring](https://mlsanity.com/paper/2605.12398/) (2026)
- [One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification Policies](https://mlsanity.com/paper/2607.21143/) (2026)
- [Generative Query Expansion with Multilingual LLMs for Cross-Lingual Information Retrieval](https://mlsanity.com/paper/2511.19325/) (2025)
- [Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition](https://mlsanity.com/paper/2602.19385/) (2026)
- [Policy-Grounded Dynamic Facet Suggestions for Job Search](https://mlsanity.com/paper/2605.16479/) (2026)
- [SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads](https://mlsanity.com/paper/2607.23121/) (2026)
- [Unified Semantic Modeling Framework for Large-Scale Job Understanding at LinkedIn](https://mlsanity.com/paper/2607.24783/) (2026)
- [KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search](https://mlsanity.com/paper/2608.21365/) (2026)
- [Query Rewriting for Complex Object Segmentation in 4D Gaussian Representations](https://mlsanity.com/paper/2609.02664/) (2026)

## Abstract (arXiv)

Query expansion (QE) enhances retrieval by incorporating relevant terms, with large language models (LLMs) offering an effective alternative to traditional rule-based and statistical methods. However, LLM-based QE suffers from a fundamental limitation: it often fails to generate relevant knowledge, degrading search performance. Prior studies have focused on hallucination, yet its underlying cause--LLM knowledge deficiencies--remains underexplored. This paper systematically examines two failure cases in LLM-based QE: (1) when the LLM lacks query knowledge, leading to incorrect expansions, and (2) when the query is ambiguous, causing biased refinements that narrow search coverage. We conduct controlled experiments across multiple datasets, evaluating the effects of knowledge and query ambiguity on retrieval performance using sparse and dense retrieval models. Our results reveal that LLM-based QE can significantly degrade the retrieval effectiveness when knowledge in the LLM is insufficient or query ambiguity is high. We introduce a framework for evaluating QE under these conditions, providing insights into the limitations of LLM-based retrieval augmentation.