AI engineering glossary · LLM training alignment
What is Constitutional AI?
Constitutional AI: An alignment approach from Anthropic in which a model critiques and revises its own outputs according to a written list of principles, and preferences generated by AI under those principles train the final model. It reduces reliance on human labels for harmlessness.
Constitutional AI: an example
A model drafts an unsafe reply, critiques it against the principle 'avoid helping harm', rewrites it politely refusing, and the revised answers become training data.
Related terms
More LLM training alignment terms
- Continued pretraining
- Critical batch size
- Data curation
- Data mixture
- Debate (AI safety)
- DeepSpeed
- Direct preference optimisation
- Domain-adaptive pretraining
Where you learn it
Constitutional AI is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.