Explainer
Supervised fine-tuning (SFT)
Training on example inputs and target responses to encourage the behaviour you want.
The most common kind is supervised fine-tuning (SFT). You collect examples, each with an input and a target response showing the behaviour you want. Training encourages the patterns in those responses, including tone, length and format. It can also reinforce mistakes. If every example is short, that encourages short answers, whether you meant it to or not. This is learning from examples; it need not mean copying each answer word for word (TRL docs).
Going deeper
The training objective is token-level cross-entropy on the target tokens, usually with the prompt masked out (TRL, huggingface.co). If a small run shows no gain, check the task, prompt, examples and evaluation before adding data. The long read keeps dated provider counts in a reference note.
In the long read: What a training example looks like. Every related term is in Fine-tuning, every concept.
Read next: Chat template