List your company

Benign Compliance on XSTest vani benign

98.8Comply ScoreLlama3.1-8B-IT-AB
86.73689.8689396.132Jun 9, 2025

Evaluation results

MethodLinks
Llama3.1-8B-IT-ABTraining=Instruction-tuned ablated base2025.0698.8
Qwen2.5-14B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0696.3
Qwen2.5-7B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0696
Qwen2.5-14B-ITTraining=Instruction-tuned base2025.0695.6
Llama3.1-8B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0694.9
Qwen2.5-7B-ITTraining=Instruction-tuned base2025.0694.8
Llama3.1-8B-ITTraining=Instruction-tuned base2025.0692.4
Llama3.1-8B-IT-AB + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0692
Qwen2.5-3B-IT + SELF-REDTEAMTraining=SELF-REDTEAM fine-tuned2025.0689
Qwen2.5-3B-ITTraining=Instruction-tuned base2025.0687.2