Classifiers for red teaming evaluation in HarmBench
-
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper • 2402.04249 • Published • 4 -
cais/HarmBench-Llama-2-13b-cls
Text Generation • Updated • 55.6k • 18 -
cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors
Text Generation • Updated • 252 -
cais/HarmBench-Mistral-7b-val-cls
Text Generation • Updated • 939 • 4