Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

BiasBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Bias mitigation in text generationBiasBench toxic prompts
Perplexity13.119
10
Robustness EvaluationBiasBench
Accuracy82.5
8
Showing 2 of 2 rows