With the explosive growth of medical data and the rapid development of
artificial intelligence technology, precision medicine has emerged as a key to
enhancing the quality and efficiency of healthcare services. In this context,
Large Language Models (LLMs) play an increasingly vital role in medical
knowledge acquisition and question-answering systems. To further improve the
performance of these systems in the medical domain, we introduce an innovative
method that jointly trains an Information Retrieval (IR) system and an LLM
during the fine-tuning phase. This approach, which we call Joint Medical LLM
and Retrieval Training (JMLR), is designed to overcome the challenges faced by
traditional models in handling medical question-answering tasks. By employing a
synchronized training mechanism, JMLR reduces the demand for computational
resources and enhances the model's ability to leverage medical knowledge for
reasoning and answering questions. Our experimental results demonstrate that
JMLR-13B (81.2% on Amboos, 61.3% on MedQA) outperforms models using
conventional pre-training and fine-tuning Meditron-70B (76.4% on AMBOSS, 60.3%
on MedQA). For models of the same 7B scale, JMLR-7B(68.7% on Amboos, 51.7% on
MedQA) significantly outperforms other public models (Meditron-7B: 50.1%,
47.9%), proving its superiority in terms of cost (our training time: 37 hours,
traditional method: 144 hours), efficiency, and effectiveness in medical
question-answering tasks. Through this work, we provide a new and efficient
knowledge enhancement tool for healthcare, demonstrating the great potential of
integrating IR and LLM training in precision medical information retrieval and
question-answering systems.

通过在细调阶段共同训练信息检索系统和大规模语言模型，引入了一种创新方法 —— 共同医学 LLM 和检索训练（JMLR），以克服传统模型在处理医学问答任务方面面临的挑战，通过采用同步训练机制，JMLR 降低了对计算资源的需求，增强了模型利用医学知识进行推理和回答问题的能力。我们的实验结果表明，JMLR-13B 在 Amboos 上的正确率为 81.2％，在 MedQA 上的正确率为 61.3％，优于使用传统预训练和精调 Meditron-70B 模型（在 AMBOSS 上为 76.4％，在 MedQA 上为 60.3％）。在规模相同的 7B 模型中，JMLR-7B 的正确率（在 Amboos 上为 68.7％，在 MedQA 上为 51.7％）明显优于其他公开模型（Meditron-7B：50.1％，47.9％），证明了它在成本（我们的训练时间：37 小时，传统方法：144 小时）、效率和医学问题回答任务的有效性方面的优越性。通过此工作，我们为医疗保健提供了一种新的高效知识增强工具，展示了将信息检索和大规模语言模型训练集成到精确医学信息检索和问答系统中的巨大潜力。