AI engineering glossary · Evals guardrails AI security
What is constitutional classifiers?
Constitutional classifiers: Safety classifiers trained on synthetic data generated from a written set of rules, a constitution, that define allowed and disallowed content. Placed around a model, they screen inputs and outputs to resist jailbreaks while aiming to keep refusals of harmless requests low.
Constitutional classifiers: an example
A classifier trained from written rules about weapons information blocks a jailbreak attempt while allowing a chemistry homework question.
Related terms
More Evals guardrails AI security terms
- Content moderation
- Crescendo attack
- Cross-tenant leakage
- Data exfiltration
- Data masking
- Data poisoning
- DeepEval
- Defence in depth
Where you learn it
Constitutional classifiers is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.