Definition

Constitutional AI (Bai et al., 2022) trains a helpful, harmless and honest model with less human feedback. A written set of principles, the constitution, guides self-improvement.

  1. Supervised phase: the model critiques its own responses against the principles and revises them; the revisions become training data.
  2. RLAIF phase: an AI model judges which responses are better; Reinforcement Learning from AI Feedback replaces human labeling.

Result: less harmful and less evasive than standard RLHF, and the values are transparent and auditable.

Appears in