Constitutional AI: Harmlessness from AI Feedback
Paper • 2212.08073 • Published • 4
Papers: RLAIF
-
-
Specific versus General Principles for Constitutional AI
Paper • 2310.13798 • Published • 3 -
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Paper • 2501.18837 • Published • 10 -
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Paper • 2601.04603 • Published -
Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI
Paper • 2511.01689 • Published • 5