COGNET-MD
收藏资源简介:
COGNET-MD是由比雷埃夫斯大学信息学系创建的医疗领域大型语言模型评估数据集,包含542个选择题,涵盖精神病学、牙科、肺病学、皮肤病学和内分泌学等多个医疗领域。数据集通过与多位医疗专家合作构建,题目难度各异,旨在评估模型在医疗文本解释方面的能力。该数据集可用于提高医疗AI应用的部署和使用效率,解决医疗领域中AI模型评估数据不足的问题。
COGNET-MD is a medical domain large language model (LLM) evaluation dataset developed by the Department of Informatics of the University of Piraeus. It contains 542 multiple-choice questions covering multiple medical specialties including psychiatry, dentistry, pulmonology, dermatology, and endocrinology. Constructed in collaboration with multiple medical experts, the dataset includes questions of varying difficulty levels, aiming to evaluate a model's ability to interpret medical texts. This dataset can be used to improve the deployment and utilization efficiency of medical AI applications, and address the shortage of evaluation data for AI models in the medical field.

- 1COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain信息学系,比雷埃夫斯大学 · 2024年



