AI Glossary

Constitutional AI

noun phraseAI trainingpreferred in this glossary

Method of training an AI model to be harmless in which human oversight consists of rules or principles, without human labels identifying harmful outputs. The model critiques and revises its answers, then learns from AI feedback comparing answers.

Source: Anthropic, Constitutional AI (opens in a new tab) (adapted)

Adapted: combines the paper's description of human oversight with its self-critique and AI-feedback training stages. Source: Anthropic, Constitutional AI (opens in a new tab)

In plain language

Use stated principles and model feedback to train responses that avoid harm.

In a sentence

  • The researchers used Constitutional AI to train from model critiques and comparisons.
  • The report described the principles used in the Constitutional AI training procedure.

Examples written for this glossary

Usage note

The entry names a training method. A later document setting out a model's principles does not by itself establish which training procedure was used.

  • Method name

    Origin

    An origin source records where a term or practice came from. Anthropic's December 2022 research page names the method and describes training without human labels identifying harmful outputs.

    Source: Anthropic, Constitutional AI (opens in a new tab)

See also

  • Emergent misalignment

    Effect in which fine-tuning a model on a narrow task, such as writing insecure code, produces misaligned behavior on unrelated prompts.

  • Corrigibility

    Property of an AI system of cooperating with interventions its creators regard as corrective, including shutdown or changes to its preferences, despite default incentives for rational agents to resist.

  • Post-training

    Training after pretraining that refines a model's behavior, including following instructions and matching human preferences, and can unlock new skills.

  • LLM-as-a-judge

    Evaluation method that uses a large language model to score the output of an AI system, including answers to open-ended questions.

Cite this term.

CC BY 4.0, attribution required.

This term

Orbyt Labs, Constitutional AI (AI Glossary), Nov 14, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/constitutional-ai

The dataset (JSON)

Orbyt Labs Glossaries (Nov 14, 2026), https://www.orbytlabs.ai/glossary#dataset

Last updated .