single source · post-training
Supervised fine-tuning on Chain of Causation data
Uses CoC data to teach the model to generate reasoning traces through imitation.
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.
Also called supervised fine-tuning on CoC data, SFT on the CoC dataset.
Filed under post-training › supervised fine-tuning