Few-Shot Prompting

Assigning a role or identity to the model.

Explicit output constraints (format, tone).

Using markers to isolate context segments.

Sampling multiple outputs and selecting consensus.

The text (and possibly other modalities) given to an LLM to condition its output behavior.

Crafting prompts to elicit desired behavior, often using role, structure, constraints, and examples.

Task instruction without examples.

One example included to guide output.