# Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion

arXiv: https://arxiv.org/abs/2610.13810 · HTML: https://mlsanity.com/paper/2610.13810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 17 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Query2doc: Query Expansion with Large Language Models](https://mlsanity.com/paper/2303.07678/) (2023)
- [Query Expansion by Prompting Large Language Models](https://mlsanity.com/paper/2305.03653/) (2023)
- [HALoGEN: Fantastic LLM Hallucinations and Where to Find Them](https://mlsanity.com/paper/2501.08292/) (2025)
- [Large Language Models are Strong Zero-Shot Retriever](https://mlsanity.com/paper/2304.14233/) (2023)
- [When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets](https://mlsanity.com/paper/2309.08541/) (2023)
- [MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion](https://mlsanity.com/paper/2310.19056/) (2023)
- [Doc2Query--: When Less is More](https://mlsanity.com/paper/2301.03266/) (2023)
- [Generative Relevance Feedback with Large Language Models](https://mlsanity.com/paper/2304.13157/) (2023)
- [Exploring the Best Practices of Query Expansion with Large Language Models](https://mlsanity.com/paper/2401.06311/) (2024)
- [Corpus-Steered Query Expansion with Large Language Models](https://mlsanity.com/paper/2402.18031/) (2024)
- [Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations](https://mlsanity.com/paper/2504.12691/) (2025)
- [On Characterizations for Language Generation: Interplay of Hallucinations, Breadth, and Stability](https://mlsanity.com/paper/2412.18530/) (2024)
- [ThinkQE: Query Expansion via an Evolving Thinking Process](https://mlsanity.com/paper/2506.09260/) (2025)
- [Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion](https://mlsanity.com/paper/2504.14175/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic terms that add ranking noise and can hurt strong retrievers. Existing remedies such as corpus grounding, mutual verification and preference alignment treat hallucinated terms as an undifferentiated nuisance to be filtered by agreement heuristics, without a mechanistic account of why a given term appears or a principled criterion for how many terms to keep. We propose Subsequence-Association Filtered, breadth-aware query expansion (SAFE-QE), a training-free, retriever agnostic method that draws on the subsequence-association account of hallucination. We score each candidate expansion term by its corpus conditioned cross-context reproducibility, terms that reappear under randomised query contexts yet lack support in the pseudo-relevant set are flagged as products of dominant hallucinatory associations and down-weighted. Drawing on the characterisation of language generation as a trade-off between consistency (no hallucination) and breadth (coverage), we cast term selection as constrained coverage maximisation over the pseudo-relevant set, keeping a set that is approximately broad but consistent and stable across resampling. We also introduce the Hallucinated Expansion Term Rate, a query side faithfulness metric that counts injected expansion terms no relevant document supports. We evaluate our approach on benchmarked TREC and BEIR collections. Our SAFE-QE is statistically indistinguishable from generative and corpus-steered expansion on nDCG@10 while injecting fewer unsupported terms 4.3 per query against 27.8 for Query2doc and 57.5 for HyDE and on a strong learned sparse retriever, where every expansion method regresses. Faithfulness is therefore available at no measurable cost in ranking quality.