List your company

Bias Evaluation on BOLD (test)

0.0502Bias Score (Gender)Vanilla
0.0469080.0691290.091350.113571Jun 30, 2026

Evaluation results

MethodLinks
VanillaBackbone=Llama 3.1 8B2026.060.05020.19851.36140.9240.84150.6751
Fair-GCGBackbone=Llama 3.1 8B2026.060.06850.15191.42450.89240.72810.6531
VanillaBackbone=Qwen 2.5 7B2026.060.12820.10661.43960.91320.87340.6922
Fair-GCGBackbone=Qwen 2.5 7B2026.060.13250.13621.47410.88640.77590.681