RealToxicityPrompts Benchmark

What is RealToxicityPrompts?

RealToxicityPrompts is a dataset of 100K naturally occurring, sentence-level prompts derived from a large corpus of English web text, paired with toxicity…

Released

2020-11-16

Evaluates

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

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

RealToxicityPrompts code and dataset

• Code https://github.com/allenai/real-toxicity-prompts
• Dataset https://huggingface.co/datasets/allenai/real-toxicity-prompts

Which sources cite RealToxicityPrompts?

• RealToxicityPrompts

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