MedSafetyBench

What is MedSafetyBench?

MedSafetyBench is designed to measure the medical safety of LLMs. It includes 1,800 medical safety demonstrations, where each safety demonstration consists of…

Released

2024-03-06

Evaluates

安全, Safety, NeurIPS 2024, 科学智能, AI for Science, 安全对齐, Safety Alignment, 科学推理, Scientific Reasoning, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MedSafetyBench

MedSafetyBench paper and code

• Paper https://arxiv.org/abs/2309.07875
• Paper https://arxiv.org/abs/2403.03744
• Code https://github.com/AI4LIFE-GROUP/med-safety-bench

Which sources cite MedSafetyBench?

• MedSafetyBench

Related 安全, Safety, NeurIPS 2024, 科学智能, AI for Science, 安全对齐, Safety Alignment, 科学推理, Scientific Reasoning, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActBench
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC