LLM Reference
Concepts & capability filters

supervised fine-tuning

Supervised fine-tuning (SFT) adapts a pretrained model on labeled instruction–response pairs so it follows directives and output formats, and typically precedes preference tuning like RLHF.

Category
Not classified
Difficulty
Not classified
Aliases
None tracked
Last reviewed
2026-07-02

Key facts

  • SFT improves instruction adherence and formatting but does not guarantee factual accuracy — a well-tuned model can still hallucinate.

Models Mentioning supervised fine-tuning(12)