LearnBenchStart learning →

AI Research Scientist · Pretraining & Fine-Tuning Objectives

Supervised fine-tuning of language models

Real lesson card · Page 1 of 3

Supervised fine-tuning of language models

Supervised fine-tuning

Supervised fine-tuning (SFT) continues training a pretrained language model on labeled input-output pairs, using a supervised loss that pushes the model’s output toward a specific target response — unlike pretraining, which predicts the next token from raw, unlabeled text.
Example
Given the instruction Summarize this email paired with a human-written summary, SFT trains the model to produce that summary, not just to continue the email’s text.

Recall check from the same lesson

You could get the same instruction-following capability by simply continuing next-token pretraining on more raw text that happens to contain instructions and answers, without ever building labeled input-output pairs.

Sources

· Editorial policy

One sitting · 20–30 minutes

A focused session on your AI Research Scientist interview

LearnBench starts from what you already know — skip what you have, master what you’re missing.

Start now

More Pretraining & Fine-Tuning Objectives questions