Supervised fine-tuning
Training on curated input/output pairs so the model adopts a specific task or response style.
By Lattice editorial · Entry last reviewed · method
What it implies
The baseline post-training step. Its value depends entirely on example quality: a thousand mediocre pairs produce a model that is reliably mediocre. SFT teaches format and behaviour; it does not reliably teach knowledge, which is what people expect it to do and what it cannot do.
Tools in this index
Related terms
- LoRATraining small low-rank matrices alongside frozen weights, so you can adapt a large model without touching it.
- Direct preference optimisationAligning a model to human preferences without an explicit reward model, by optimising on chosen-versus-rejected pairs.
- DistillationTraining a smaller model against the outputs of a larger one, to get most of the behaviour at a fraction of the cost.