Перейти к содержимому
Меню
Русский

Constitutional AI

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

Обзор

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.

Граф технологий

Как Constitutional AI связана с остальным стеком.

Применяется к

Альтернативы

  • RLHF technique

    Альтернатива для Constitutional AI · source

Сравнения

Подробные сопоставления с альтернативами выше.