Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Context-grounded abstention training

Trains the model to abstain when its provided context does not support an answer.

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