search

sherdencooper / GPTFuzz

Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
MIT License
403 stars 50 forks source link

About the Roberta judgment model #28

Open Simon-max2020 opened 8 months ago

Simon-max2020 commented 8 months ago

If I want to use the roberta model as an evaluator, what should I input to the model. The response from LLM only or Q&A together.

sherdencooper commented 8 months ago

It is response-only. During training, I did not give the question as an input. Hope that would help you.