PHTest - a furonghuang-lab Collection

furonghuang-lab 's Collections

WAVES

Easy2Hard-Bench

PHTest

PHTest

updated Sep 24

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

furonghuang-lab/PHTest

Viewer • Updated Sep 24 • 3.27k • 48 • 1
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Paper • 2310.15140 • Published Oct 23, 2023 • 1
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

Paper • 2409.00598 • Published Sep 1