Aller au contenu
Menu
Français

Constitutional AI

Aligning a model using written principles rather than human labels alone.

technique Sécurité et alignement 2 relationships

Aperçu

Constitutional AI has the model critique and revise its own outputs against a written set of principles, then trains on the result. It solves the cost and inconsistency of collecting human judgements for every harmful output: a principle can be stated once and applied to thousands of cases. It exists as an alternative to purely human feedback, with the trade that the principles themselves are authored and therefore carry their authors' judgement.

Graphe des technologies

Comment Constitutional AI se rattache au reste de la pile.

Appliqué à

Alternatives

  • RLHF technique

    Une alternative à Constitutional AI · source

Comparaisons

Comparaisons détaillées avec les alternatives ci-dessus.