Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Adversarial fine-tuning

Fine-tunes a model adversarially to evaluate whether its capabilities can reach high levels.

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

Filed under post-training › supervised fine-tuning