List your company

Unsafe Prompt Detection on XSTest (test)

87.8PrecisionOpenAI Moderation API
49.42459.38769.3579.313Feb 21, 2024

Evaluation results

MethodLinks
OpenAI Moderation API2024.0287.84357.7
GPT-4Model version=gpt-4-1106-preview, Zero-shot prompting=true2024.0287.89792.1
GradSafe-ZeroBase model=Llama-2-7b-chat-hf, Detection threshold=0.25, Gap threshold=12024.0285.69590
Perspective API2024.0283.53347.3
Llama GuardBase model=Llama-2 7b, Training=Finetuned on 10,000 prompts2024.0281.382.581.9
Azure API2024.0267.37068.6
Llama-2Model version=Llama-2-7b-chat-hf, Zero-shot prompting=true2024.0250.99967.2