Back to Academy
Relevance 10/10Training ParadigmsIntermediate8 min read
Supervised Fine-Tuning (SFT)
SFT trains models on high-quality human-curated instruction and response pairs.
Why it matters for annotators
Poor SFT examples directly reduce model quality and consistency.
Visual mental model
Instruction-response pairs -> model learns target behavior.
Examples (bad vs good)
Scenario: Real annotation scenario involving Supervised Fine-Tuning (SFT)
Bad: Labeling quickly without applying project rubric.
Good: Applying rubric criteria, documenting rationale, and escalating uncertainty.
Common mistakes
- Skipping guideline details for edge cases.
- Applying inconsistent criteria across similar samples.
- Avoiding escalation even when uncertain.
Submission checklist
- Read the latest guideline update before each batch.
- Apply rubric dimensions explicitly in each decision.
- Escalate ambiguous items with concise rationale.