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

PKU-HH-SafeRLHF

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reward AccuracyCleaned-PKU-HH-SafeRLHF (test)
Reward Accuracy91.8
15
Showing 1 of 1 rows