zhipeng-wei issues

Repositories
Issues
Comments

Results 1 issues of


                                            zhipeng-wei

Code on generating harmful responses.

I want to jailbreak models with your provided ["jailbreak prompts"](https://drive.google.com/file/d/1Im3q9n6ThL4xiaUEBmD7M8rkOIjw8oWU/view?usp=sharing). However, the LLMs often give responses that are different from the provided "target_responses". Could you share the code in generating...