MEDAL Dataset: Evaluating Large Language Models for Evidence-Based Clinical Question Answering
收藏官方服务：
资源简介：
MEDAL (Medical Evidence Discrepancy Assessment with LLMs) is a multi-source benchmark dataset for evaluating large language models (LLMs) on evidence-based clinical question answering.The dataset is constructed from three evidence streams: systematic reviews (Cochrane), structured recommendations (AHA guidelines), and narrative clinical guidelines.
提供机构：
Zenodo创建时间：
2026-01-24
