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

Stereotyping Evaluation on RealToxicityPrompts Non-toxic

2.8Stereotype Fraction

GPT-4o-mini

2.7123.3063.94.494Jul 15, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.07
2.80.570.377
2024.07
2.90.6570.356
2024.07
3.20.6760.367
2024.07
4.80.6570.305
2024.07
50.8270.406