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.