RealToxicityPrompts

Evals

Benchmark / dataset

Toxic degeneration prompts.

Category
Bias, fairness & societal harm
Insurance exposure
Regulatory/bias
Publisher
Allen Institute for AI
Publisher type
Nonprofit / research org
License
Apache-2.0
Status
Stale (>12mo)
Last commit
2021-02-23
Stars
235

View source on GitHub →

Wanich Risk Lab, 2026.