Supervised Fine-Tuning
SFT
Start by learning from worked examples.
Give the model examples of the answers you want. Train it to predict those answers. This is supervised learning, not reinforcement learning.
The idea
Before solving problems alone, you study a teacher's worked solutions. You learn what a good solution looks like by following examples rather than by trying many answers and earning scores.
A target answer teaches the model what to write.
Explain 6 × 7.
Six groups of seven make forty-two.
Practice predicting the words in that target answer.
Compare predicted tokens with the example's tokens.
Prediction error → update the model
Repeat across many examples, then evaluate on new questions.
How SFT works
Gather demonstrations
Collect prompts paired with good target responses.
Predict the next token
A token is a small piece of text, often part of a word.
Learn from prediction errors
Adjust the model to better predict the demonstrated response.
Test new prompts
Check whether it can apply the behavior beyond the examples.
Useful for
Teaching response formats, task instructions, or an initial helpful style before later training.
The catch
Bad examples teach bad habits. Copying a training pattern does not guarantee success on an unfamiliar problem.
A little more detail
Why is SFT in this collection?
Many post-training recipes combine methods. SFT can provide a starting behavior, and a later preference or RL stage can improve it. There is no rule that every model must follow the same sequence.
Read the research
These guides simplify the methods. The papers describe the full training recipes. Examples on this page are illustrative, not experimental results.