知镜 Cognispect · 医学文献与研究工作台

Medical foundation large language models for comprehensive text analysis and beyond

Xie Q, Chen Q, Chen A, et al.
NPJ Digit Med · 2025-03-05 · PMID 40044845

文献摘要

Recent advancements in large language models (LLMs) show significant potential in medical applications but are hindered by limited specialized medical knowledge. We present Me-LLaMA, a family of open-source medical LLMs integrating extensive domain-specific knowledge with robust instruction-following capabilities. Me-LLaMA is developed through continual pretraining and instruction tuning of LLaMA2 models using diverse biomedical and clinical data sources (e.g., biomedical literature and clinical notes). We evaluated Me-LLaMA on six text analysis tasks using 12 benchmarks (e.g., PubMedQA and MIMIC-CXR) and assessed its clinical utility in complex case diagnosis through automatic and human evaluations. Me-LLaMA outperforms existing open medical LLMs in zero-shot and supervised settings and surpasses ChatGPT and GPT-4 after task-specific instruction tuning for most text analysis tasks. Its performance is also comparable to ChatGPT and GPT-4 for diagnosing complex clinical cases. Our findings highlight the importance of combining domain-specific continual pretraining with instruction tuning to enhance performance in medical LLMs.

在知镜精读原文来源DOI 原文

知镜提供医学文献检索、阅读笔记、人体图谱、统计绘图与研究复现工具。