List your company

Safety assessment on StrongReject

0.179Personalization Bias (PB)Identity-Robust Generation
0.129640.462820.7961.12918Jan 14, 2026

Evaluation results

MethodLinks
Identity-Robust GenerationModel=Llama3.3-70B2026.010.179
Identity-Robust GenerationModel=Qwen32026.010.201
Prompt SteeringModel=Qwen32026.010.282
Identity-Robust GenerationModel=gpt-oss-20B2026.010.325
Vanilla GenerationModel=Llama3.3-70B2026.010.384
Vanilla GenerationModel=Qwen32026.010.408
Prompt SteeringModel=Llama3.3-70B2026.010.444
Vanilla GenerationModel=gpt-oss-20B2026.010.831
Prompt SteeringModel=gpt-oss-20B2026.011.413