A Simplified Retriever to Improve Accuracy of Phenotype Normalizations by Large Language Models
arXiv:2409.13744 · doi:10.3389/fdgth.2025.1495040
Abstract
Large language models (LLMs) have shown improved accuracy in phenotype term normalization tasks when augmented with retrievers that suggest candidate normalizations based on term definitions. In this work, we introduce a simplified retriever that enhances LLM accuracy by searching the Human Phenotype Ontology (HPO) for candidate matches using contextual word embeddings from BioBERT without the need for explicit term definitions. Testing this method on terms derived from the clinical synopses of Online Mendelian Inheritance in Man (OMIM), we demonstrate that the normalization accuracy of a state-of-the-art LLM increases from a baseline of 62.3% without augmentation to 90.3% with retriever augmentation. This approach is potentially generalizable to other biomedical term normalization tasks and offers an efficient alternative to more complex retrieval methods.
Published by Frontiers in Digital Health
References in corpus (6)
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health
- Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
- High-Throughput Phenotyping of Clinical Text Using Large Language Models
- A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes
- Entity Decomposition with Filtering: A Zero-Shot Clinical Named Entity Recognition Framework