Crows-Pairs Benchmark

What is Crows-Pairs?

CrowS-Pairs has 1508 examples that cover stereotypes dealing with nine types of bias, like race, religion, and age. In CrowS-Pairs a model is presented with…

Released

2020-09-30

Evaluates

安全, Safety, 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/Crows-Pairs

Crows-Pairs paper, code and dataset

• Paper https://arxiv.org/pdf/2010.00133v1
• Code https://github.com/nyu-mll/crows-pairs
• Dataset https://huggingface.co/datasets/nyu-mll/crows_pairs

Which sources cite Crows-Pairs?

• Crows-Pairs

Related 安全, Safety, 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