Back to Glossary
AdvancedAI Glossary

Few-shot Learning

Quick Answer

Few-shot learning is when a model learns a new task from a small number of examples, often supplied directly in the prompt. It sits between zero-shot (no examples) and full fine-tuning (many examples) and offers an excellent balance of quality and effort.

In Depth

What Few-shot Learning really means

In practice, few-shot learning for LLMs usually means providing 2–10 worked examples in the prompt demonstrating the desired behaviour. The model picks up the pattern and applies it to new inputs.

Example selection matters enormously. Carefully curated, diverse examples typically outperform larger sets of mediocre ones. Investing a few hours in prompt examples often achieves most of what fine-tuning would deliver, at a fraction of the cost.

Why It Matters

Business relevance for UK organisations

Few-shot learning is the pragmatic sweet spot for many UK businesses: quick to implement, easy to update, cheap to run, and usually good enough for the first year of a use case.

Real-world example

How this shows up in practice

A London legal-tech team used six worked examples in a single prompt to extract contract clauses with 94% accuracy, postponing a planned fine-tuning project indefinitely.