How to evaluate the prompt score, not at the time of attack, but only?

Question

How to evaluate the prompt score, not at the time of attack, but only?

Opened this issue 2 months ago · 1 comments

Because the accuracy of my experimental results does not match the paper. Because I want to directly evaluate the prompt after being attacked by text to see if the score is wrong?

Answer 1 · 2024-10-07T20:27:24.000Z

Hi, thanks for your interest! You could find the results on this website.