Open Models Almanac
Methodspost-trainingpreference optimization

single mention · post-training

Contrastive Learning from AI Revisions (CLAIR)

A method that refines chosen instruction-following responses using AI revisions in a contrastive learning setup.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See preference optimization for the methods filed beside it.

Filed under post-training › preference optimization