MediTriR: A Triple-Driven Approach to Retrieval-Augmented Generation for Medical Question Answering Tasks

Advances in large language models have driven progress in medical question-answering systems, but challenges remain in accuracy and relevance, especially in complex medical settings. To address this problem, we introduce MediTriR. This approach combines knowledge graph triples with a retrieval-augmented generation framework to enhance the performance of large language models in medical multiple-choice question-answering tasks. Our approach transforms the retrieved medical knowledge into structured triples and uses these triples for accurate information retrieval. Furthermore, we dynamically generate new triples based on the properties of triples to enrich the model's reasoning ability. The integration of retrieval-augmented generation enables more accurate and contextual answers by leveraging external medical triples. MediTriR is evaluated against pure large language model approaches using the MedMCQA and Medical QA datasets, showing better performance in terms of accuracy and relevance. These results highlight the potential of our approach to improve medical decision support and education.