RJUA-QA
收藏资源简介:
RJUA-QA是一个专为泌尿科问题解答和临床推理设计的新型医学数据集,由上海交通大学医学院附属仁济医院泌尿科与蚂蚁集团合作创建。该数据集包含2,132个精心策划的Question-Context-Answer三元组,涵盖67种常见的泌尿系统疾病,覆盖了97.6%寻求泌尿科医疗服务的患者群体。数据集通过模拟真实临床场景,结合专家知识和经验,旨在帮助大型语言模型生成可靠的诊断和医疗建议。RJUA-QA不仅是首个针对临床医学推理的中文QA数据集,还为评估和提升大型语言模型在医疗领域的应用提供了基准。
RJUA-QA is a novel medical dataset specifically designed for urological question answering and clinical reasoning, co-developed by the Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University and Ant Group. This dataset comprises 2,132 carefully curated Question-Context-Answer triplets, covering 67 common urinary system diseases that account for 97.6% of the patient population seeking urological medical services. By simulating real clinical scenarios and integrating expert knowledge and experience, it aims to assist large language models (LLMs) in generating reliable diagnoses and medical advice. RJUA-QA is not only the first Chinese QA dataset focused on clinical medical reasoning, but also provides a benchmark for evaluating and advancing the application of large language models in the medical domain.

- 1RJUA-QA: A Comprehensive QA Dataset for Urology上海交通大学医学院附属仁济医院泌尿科 · 2024年



