Enhancing Large Language Models with Retrieval-augmented Generation: A Radiology-specific Approach.

Retrieval-augmented generation (RAG) is a strategy to improve performance of large language models (LLMs) by providing the LLM with an updated corpus of knowledge that can be used for answer generation in real-time. RAG may improve LLM performance and clinical applicability in radiology by providing citable, up-to-date information without requiring model fine-tuning. In this retrospective study, a radiology-specific RAG was developed using a vector database of 3,689 articles published from January 1999 to December 2023. Performance of 5 LLMs with and without RAG on a 192-question radiology examination was compared. RAG significantly improved examination scores for GPT-4 (81.2% versus 75.5%, = .04) and Command R+ (70.3% versus 62.0%, = .02), but not for Claude Opus, Mixtral, or Gemini 1.5 Pro. RAG-System performed significantly better than pure LLMs on a 24-question subset directly sourced from (85% versus 76%, = .03). The RAG-System retrieved 21/24 (87.5%, < .001) relevant references cited in the examination's answer explanations and successfully cited them in 18/21 (85.7%, < .001) outputs. The results suggest that RAG is a promising approach to enhance LLM capabilities for radiology knowledge tasks, providing transparent, domain-specific information retrieval. ©RSNA, 2025.