Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Paper • 2501.18837 • Published • 10
Nimit Kalra
nimitkalra
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
OpenMOSS-Team/SciThinker-30B liked a dataset 11 days ago
lime-nlp/DeepScaleR_Difficulty liked a dataset 5 months ago
open-r1/DAPO-Math-17k-ProcessedOrganizations
None yet
authored 2
papers about 1 year ago