Tip2025-07-18#prompting

Your examples frame format louder than content

Few-shot learning is pattern continuation. The model is extremely sensitive to surface form, sometimes more than to the actual reasoning you intended to demonstrate.

Make every example identical in structure, pick label words that are single clean tokens, and keep lengths similar. The more rigid the template, the more reliably the model fills in the next blank.

Aha moment

Few-shot examples frame surface form first. The model copies the pattern before it understands your intention.

Try this

Make labels, punctuation, casing, separators, and example length boringly consistent.

Open NotesEntry JSON

Watch for

  • One example with a different label shape
  • Multi-token labels competing with single-token labels
  • Examples that demonstrate style drift instead of the task