Retrieval-Augmented Medical Large Language Models

Biomedical large language models (LLMs) have made significant strides, but their reliance on external retrieval mechanisms presents challenges in accuracy and computational efficiency. To address these issues, we propose MedRAG-Refine, a generative LLM designed specifically for the biomedical domain. Our model integrates a two-stage fine-tuning process, incorporating a self-reflection mechanism to improve reasoning quality. We evaluate our model on MedQA, MedMCQA, and MMLU datasets, demonstrating superior performance over state-of-the-art methods. Additionally, human evaluations confirm the enhanced accuracy and reasoning quality of our model in real-world medical tasks.