Supervised fine-tuning
Fine-tuning on example prompts paired with good answers, usually the first step of turning a base model into an assistant.
Also: SFT
In supervised fine-tuning the model is shown prompts and high-quality responses, written by people or by other models, and trained to produce the responses. This teaches the chat format, the assistant's tone and how to follow instructions. OpenAI's InstructGPT work in 2022 used about 13,000 human-written demonstrations at this stage. SFT is cheap compared with pre-training and is often followed by preference tuning, which teaches the model to choose between good and better answers rather than just imitate.