supervised fine-tuning

Post-training stage in which a pretrained language model is further trained on curated instruction–response examples so that it answers like an assistant.

3 articlesLast mentioned

Supervised fine-tuning (SFT) is a post-training technique in which a pretrained base model is trained on conversation data consisting of instruction–exemplary response pairs. The data typically comprises tens of thousands to hundreds of thousands of examples written by human annotators or synthesized by other models, with each response ending in a stop token. A model trained this way is called an instruct or chat model; it acquires a consistent assistant persona and stops generating once its answer is complete.

Because SFT is supervised learning that imitates reference answers, it is distinguished from reinforcement learning methods such as RLHF and GRPO, which learn from reward signals. Typical LLM post-training first instills format and behavior through SFT and then refines preferences and reasoning ability with RL. In a narrower sense the term also covers fine-tuning in general, where a model is further trained on task- or domain-specific data.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • AI Agent Tuning: When to Rewrite Prompts and When to Retrain WeightsAI Performance ·

    The suggested division of labor: supervised fine-tuning first, to establish format and basic reasoning; RL once the model clears a minimum capability bar.

    Read article
  • Pre-Training, Fine-Tuning and RL: Where Frontier LLMs Get Their QualityAI Performance ·

    Supervised fine-tuning (SFT) is the first post-training stage.

    Read article
  • Temperature, Attention and Context Rot: Model Mechanics Behind Agent DesignAI in Practice ·

    In the middle is LLM adaptation: supervised fine-tuning, distillation, in-context learning, LoRA (a method for cheaply fine-tuning a model by training small low…

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.