Home › Fine-Tuning & Alignment › Key term › SFT
Key term · Models

SFT

Teaching a base model to follow instructions by example.

In one line

SFT trains a model on curated instruction-and-response pairs so it learns to be helpful.

DefinitionWhat it means

Supervised Fine-Tuning, SFT, continues training a pretrained base model on a labeled dataset of instruction-response pairs, using standard supervised loss so the model learns to produce the demonstrated response style for a given prompt. It is typically the first adaptation step, turning a raw next-token predictor into a model that follows instructions and holds a conversation.

Why it mattersWhy you should care

SFT is the foundation every instruction-tuned or chat model is built on; the quality, diversity, and correctness of its demonstration data sets a ceiling on everything that comes after, including RLHF and DPO. Teams building domain-specific assistants often run a lightweight SFT pass on top of a general instruct model before layering on preference optimization.

At a glanceSee it

SFT diagram
SFT diagram 1

The inner training loop the box diagram hides — SFT masks the prompt tokens so cross-entropy loss lands only on the response, teaching the model to answer rather than parrot the question back.

SFT diagram 2

The data-curation decision behind the flat arrow — pairs whose answers sit outside the base model's knowledge train it to guess confidently, while an over-narrow set overfits style and erodes pretrained skills.

Where you see itIn the wild

  • The step between a raw pretrained checkpoint and a usable chat model.
  • Instruction datasets built from human-written or model-generated demonstrations.
  • Domain adaptation projects fine-tuning an instruct model on internal support tickets.
A living map of modern AI — kept current every morning