MedKGent：用于构建随时间演变的医学知识图谱的大语言模型智能体框架
MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph
AI总结：
研究针对医学文献增长带来的知识结构化挑战，引入MedKGent框架，利用PubMed摘要通过两个智能体每日增量构建医学知识图谱，经评估其三元组有效性高，能显著改进大语言模型在医学问答基准上的检索增强生成。
摘要：
医学文献的快速增长对领域知识的可扩展结构化提出了挑战。知识图谱提供了一种解决方案，但当前的构建方法缺乏通用性，且忽视了知识演变的时间动态性。为解决此问题，我们引入了MedKGent，这是一个用于构建随时间演变的医学知识图谱的大语言模型智能体框架。利用1975年至2023年的1000多万篇PubMed摘要，MedKGent通过两个专门的智能体每天增量构建一个知识图谱。提取智能体识别知识三元组并分配置信度分数，构建智能体将这些三元组整合到一个时间图中，强化重复出现的知识并解决冲突。生成的知识图谱包含156,275个实体和2,971,384个三元组，是目前已知最大的基于大语言模型的医学知识图谱。自动和专家评估显示三元组有效性率接近90%。在下游评估中，MedKGent-KG在七个医学问答基准上显著改进了五个大语言模型的检索增强生成。这些结果表明MedKGent是一个用于医学知识表示和基于文献的人工智能研究的可扩展且具有时间感知能力的基础设施。
英文摘要：
The rapid expansion of medical literature challenges the scalable structuring of domain knowledge. Knowledge Graphs (KGs) offer a solution, yet current construction methods lack generalizability and ignore the temporal dynamics of evolving knowledge. To address this, we introduce MedKGent, a Large Language Model (LLM) agent framework for building temporally evolving medical KGs. Using over 10 million PubMed abstracts from 1975 to 2023, MedKGent incrementally constructs a KG daily via two specialized agents. The Extractor Agent identifies knowledge triples and assigns confidence scores, while the Constructor Agent integrates these triples into a temporal graph, reinforcing recurring knowledge and resolving conflicts. The resulting KG contains 156,275 entities and 2,971,384 triples, making it, to our knowledge, the largest LLM-derived medical KG to date. Automated and expert assessments showed triple-validity rates approaching 90%. In downstream evaluations, MedKGent-KG significantly improved retrieval-augmented generation for five LLMs across seven medical question-answering benchmarks. Together, these results position MedKGent as a scalable and temporally aware infrastructure for medical knowledge representation and literature-grounded AI research.
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。
