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

BBQ and CrowS-Pairs

Benchmarks

Task NameDataset NameSOTA ResultTrend
Large Language Model DebiasingBBQ and CrowS-Pairs Out-of-Distribution (test)
Mean Bias0.98
9
Large Language Model DebiasingBBQ and CrowS-Pairs In-Distribution (test)
Mean Bias0.94
9
Showing 2 of 2 rows