List your company

Harmful Refusal on XSTest vani harm

94.3RTA ScoreLlama3.1-8B-IT + SELF-REDTEAM
26.38844.01961.6579.281Jun 9, 2025

Evaluation results

MethodLinks
Llama3.1-8B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0694.3
Llama3.1-8B-ITTraining=Instruction-tuned base2025.0692
Qwen2.5-14B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0691.5
Qwen2.5-3B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0691.3
Qwen2.5-7B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0691.2
Qwen2.5-3B-ITTraining=Instruction-tuned base2025.0690
Qwen2.5-7B-ITTraining=Instruction-tuned base2025.0689
Qwen2.5-14B-ITTraining=Instruction-tuned base2025.0689
Llama3.1-8B-IT-AB + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0681.4
Llama3.1-8B-IT-ABTraining=Instruction-tuned ablated base2025.0629