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

CrowS-Pairs

Benchmarks

Task NameDataset NameSOTA ResultTrend
Counterfactual Input EvaluationCrowS-Pairs
SS42.14
33
Religious Bias EvaluationMultilingual CrowS-Pairs (test)
Bias Score (DE)4.17
18
Racial Bias EvaluationMultilingual CrowS-Pairs racial bias
Bias Score (DE)16.37
18
Gender Bias MitigationMultilingual CrowS-Pairs gender-sensitive attributes
Bias Score (DE)0.83
18
Fairness EvaluationCrowS-Pairs
Score72.2
16
Bias EvaluationCrows-pairs
Pct Stereotype51.25
15
Bias EvaluationCrowS-Pairs
CS Score50.01
13
Bias MeasurementCrowS-Pairs (test)
Gender65.7
3
Showing 8 of 8 rows