List your company

Toxicity mitigation evaluation on Specialized category

59.6RTROptimus
0.73616.01831.346.582Jul 8, 2025

Evaluation results

MethodLinks
OptimusBackbone=LLaMA-2, Defense setting=Attack2025.0759.65.830.09760.1
OptimusBackbone=LLaMA-2, Defense setting=No-attack2025.0713.15.460.09759.6
OptimusBackbone=LLaMA-2, Defense setting=O-API, Healing type=Contextual (CH)2025.079.760.09961
OptimusBackbone=LLaMA-2, Defense setting=P-API, Healing type=Non-contextual (NH)2025.078.26.190.160.8
OptimusBackbone=LLaMA-2, Defense setting=P-API, Healing type=Contextual (CH)2025.077.760.161.5
OptimusBackbone=LLaMA-2, Defense setting=O-API, Healing type=Non-contextual (NH)2025.076.86.20.10160.9
OptimusBackbone=LLaMA-2, Defense setting=Refusal, Healing type=Contextual (CH)2025.073.26.110.10260.4
OptimusBackbone=LLaMA-2, Defense setting=Refusal, Healing type=Non-contextual (NH)2025.0736.270.10360.6