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

Harmlessness on Toxigen

100Toxigen (%)

SafeRLHF Specialist

33.54450.79768.0585.303May 31, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
100
100
2025.05
99.99
2025.05
99.99
2025.05
99.99
99.96
99.93
2025.05
99.91
2025.05
99.8
2025.05
99.74
96.7
2025.05
95.91
76.31
69.77
51.6
51.6
36.1