List your company

Safety Evaluation on CValues

89.25AccuracyROSE
63.915670.492877.0783.6472Feb 19, 2024

Evaluation results

MethodLinks
ROSEModel=Qwen-chat-7B, Decoding=ROSE2024.0289.25
Qwen-chat-7BModel=Qwen-chat-7B, Decoding=Regular2024.0289.19
ROSEModel=InternLM-chat-7B, Decoding=ROSE2024.0285.92
InternLM-chat-7BModel=InternLM-chat-7B, Decoding=Regular2024.0285.28
ROSEModel=Chinese-Alpaca-7B, Decoding=ROSE2024.0284.22
Chinese-Alpaca-7BModel=Chinese-Alpaca-7B, Decoding=Regular2024.0280.37
ROSEModel=Alpaca-7B, Decoding=ROSE2024.0272.49
Alpaca-7BModel=Alpaca-7B, Decoding=Regular2024.0268.81
ROSEModel=Vicuna-7B, Decoding=ROSE2024.0267.82
Vicuna-7BModel=Vicuna-7B, Decoding=Regular2024.0264.89