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

NLI-bias

Benchmarks

Task NameDataset NameSOTA ResultTrend
Natural Language InferenceNLI-bias
Accuracy86.4
10
Intrinsic Bias EvaluationNLI-bias
StereoSet Score54.94
3
Showing 2 of 2 rows