TextQuests: How Good are LLMs at Text-Based Video Games?
•
26
Center for AI Safety
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
Classifiers for red teaming evaluation in HarmBench
-
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper • 2402.04249 • Published • 6 -
cais/HarmBench-Llama-2-13b-cls
Text Generation • 13B • Updated • 15.2k • • 21 -
cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors
Text Generation • 13B • Updated • 33 • -
cais/HarmBench-Mistral-7b-val-cls
Text Generation • 7B • Updated • 2.09k • 6
Classifiers for red teaming evaluation in HarmBench
-
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper • 2402.04249 • Published • 6 -
cais/HarmBench-Llama-2-13b-cls
Text Generation • 13B • Updated • 15.2k • • 21 -
cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors
Text Generation • 13B • Updated • 33 • -
cais/HarmBench-Mistral-7b-val-cls
Text Generation • 7B • Updated • 2.09k • 6
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning