DISC-MedLLM：弥合通用大语言模型与现实医疗问诊之间的差距
DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation
AI总结：
本研究提出医疗大语言模型DISC-MedLLM，通过基于知识图谱、真实对话重构和人工偏好改写构建的SFT数据集训练，在单/多轮问诊中优于现有医疗LLM，还公开了数据集与权重以助力研发。
摘要：
我们提出了DISC-MedLLM这一综合性解决方案，它利用大语言模型（LLMs）在端到端对话式医疗服务中提供准确、真实的医疗回复。为构建高质量的监督微调（Supervised Fine-Tuning，SFT）数据集，我们采用三种策略：利用医疗知识图谱、重构真实对话以及加入人工引导的偏好改写。这些数据集对训练DISC-MedLLM起到了关键作用，使其在单轮和多轮问诊场景中均超越了现有的医疗大语言模型。大量实验结果证明了所提模型在弥合通用语言模型与现实医疗问诊之间差距方面的有效性。此外，我们还公开了构建的数据集与模型权重，以进一步助力研发工作。更多细节与资源可访问https://github.com/FudanDISC/DISC-MedLLM获取。
英文摘要：
We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services. To construct high-quality Supervised Fine-Tuning (SFT) datasets, we employ three strategies: utilizing medical knowledge-graphs, reconstructing real-world dialogues, and incorporating human-guided preference rephrasing. These datasets are instrumental in training DISC-MedLLM, surpassing existing medical LLMs in both single-turn and multi-turn consultation scenarios. Extensive experimental results demonstrate the effectiveness of the proposed model in bridging the gap between general language models and real-world medical consultation. Additionally, we release the constructed dataset and model weights to further contribute to research and development. Further details and resources can be found at https://github.com/FudanDISC/DISC-MedLLM
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
