Ir para o conteúdo
Menu
Português

Constitutional AI

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

technique Segurança e alinhamento 2 relationships

Visão geral

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.

Grafo de tecnologias

Como Constitutional AI se liga ao resto do stack.

Aplicado a

Alternativas

  • RLHF technique

    Uma alternativa a Constitutional AI · source

Comparações

Comparações detalhadas com as alternativas acima.