Alignment & Preference Learning · 2022

Constitutional AI: Harmlessness from AI Feedback (RLAIF)

Yuntao Bai, Saurav Kadavath, Sandipan Kundu, et al.

Replaced most human-labeled harmlessness feedback with model-generated feedback governed by a written set of principles, removing the need for large volumes of human labels on harmful content to train a harmless assistant.

Editorial record

Plain-language summary

In a supervised phase the model critiques and revises its own responses against a short list of natural-language principles (a 'constitution'), and in an RL phase a model rather than humans ranks response pairs for harmlessness to train the preference model (RLAIF). This let the assistant refuse or push back on harmful requests while explaining its reasoning instead of giving evasive non-answers. It cut human labeling of toxic content and made the value targets explicit and editable as written rules.

Knowledge graph

Relationships

Descendants

Source record

Provenance

Record ID
P-204
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.