# Ontology-Guided Query Expansion for Biomedical Document Retrieval using Large Language Models

arXiv: https://arxiv.org/abs/2508.11784 · HTML: https://mlsanity.com/paper/2508.11784/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval](https://mlsanity.com/paper/2307.00589/) (2023)
- [Dense Text Retrieval based on Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.14876/) (2022)
- [SciRepEval: A Multi-Format Benchmark for Scientific Document Representations](https://mlsanity.com/paper/2211.13308/) (2022)
- [How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval](https://mlsanity.com/paper/2302.07452/) (2023)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval](https://mlsanity.com/paper/1910.10687/) (2019)
- [Information Retrieval: Recent Advances and Beyond](https://mlsanity.com/paper/2301.08801/) (2023)
- [Query expansion techniques for information retrieval: A survey](https://mlsanity.com/paper/1708.00247/) (2017)
- [BERT-QE: Contextualized Query Expansion for Document Re-ranking](https://mlsanity.com/paper/2009.07258/) (2020)
- [BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers](https://mlsanity.com/paper/2404.18443/) (2024)
- [Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators](https://mlsanity.com/paper/2111.13057/) (2021)
- [On-the-fly Definition Augmentation of LLMs for Biomedical NER](https://mlsanity.com/paper/2404.00152/) (2024)
- [Improving Conversational Passage Re-ranking with View Ensemble](https://mlsanity.com/paper/2304.13290/) (2023)
- [Simple Domain Adaptation for Sparse Retrievers](https://mlsanity.com/paper/2401.11509/) (2024)

## Abstract (arXiv)

Effective Question Answering (QA) on large biomedical document collections requires effective document retrieval techniques. The latter remains a challenging task due to the domain-specific vocabulary and semantic ambiguity in user queries. We propose BMQExpander, a novel ontology-aware query expansion pipeline that combines medical knowledge - definitions and relationships - from the UMLS Metathesaurus with the generative capabilities of large language models (LLMs) to enhance retrieval effectiveness. We implemented several state-of-the-art baselines, including sparse and dense retrievers, query expansion methods, and biomedical-specific solutions. We show that BMQExpander has superior retrieval performance on three popular biomedical Information Retrieval (IR) benchmarks: NFCorpus, TREC-COVID, and SciFact - with improvements of up to 22.1% in NDCG@10 over sparse baselines and up to 6.5% over the strongest baseline. Further, BMQExpander generalizes robustly under query perturbation settings, in contrast to supervised baselines, achieving up to 15.7% improvement over the strongest baseline. As a side contribution, we publish our paraphrased benchmarks. Finally, our qualitative analysis shows that BMQExpander has fewer hallucinations compared to other LLM-based query expansion baselines.