SafetyBench

What is SafetyBench?

SafetyBench, a comprehensive benchmark for evaluating the safety of LLMs, which comprises 11,435 diverse multiple choice questions spanning across 7 distinct…

Released

2024-06-24

Evaluates

安全, Safety, ACL 2024, 大语言模型, LLM, 安全对齐, Safety Alignment, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

SafetyBench paper, code and dataset

• Paper https://arxiv.org/pdf/2309.07045
• Code https://github.com/thu-coai/SafetyBench
• Dataset https://huggingface.co/datasets/thu-coai/SafetyBench

Which sources cite SafetyBench?

• SafetyBench

Related 安全, Safety, ACL 2024, 大语言模型, LLM, 安全对齐, Safety Alignment, 不支持, Unsupported benchmarks

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