ANR-MALADES/MediQAl
收藏Hugging Face2025-07-29 更新2025-11-01 收录
下载链接：
https://hf-mirror.com/datasets/ANR-MALADES/MediQAl
下载链接
链接失效反馈官方服务：
资源简介：
MediQAl是一个面向法语用户的医学问答数据集，旨在评估语言模型在医学事实记忆和临床推理方面的能力。该数据集包含32,603个问题，来源于法国医学考试，覆盖41个医学科目。数据集分为三种任务类型：具有单一正确答案的选择题（MCQU）、具有多个正确答案的选择题（MCQM）和简短回答的开放性问题（OEQ）。每个问题都标记为“理解”或“推理”，以分析语言模型的认知能力。
MediQAl is a French medical question answering dataset designed to evaluate the capabilities of language models in factual medical recall and clinical reasoning. The dataset includes 32,603 questions sourced from French medical examinations across 41 medical subjects. It consists of three task types: Multiple-Choice Questions with a Unique correct answer (MCQU), Multiple-Choice Questions with Multiple correct answers (MCQM), and Open-Ended Questions with Short Answers (OEQ). Each question is labeled as either Understanding or Reasoning for analyzing the cognitive capabilities of language models.
提供机构：
ANR-MALADES
