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.
Related Terms
Continue exploring
Zero-shot Learning
Zero-shot learning is when a model performs a task it was never explicitly trained on, by generalising from related knowledge. Modern LLMs routinely perform useful zero-shot classification, extraction and generation tasks with no task-specific training examples.
TechnicalPrompt Engineering
Prompt engineering is the practice of designing the text instructions given to a language model to produce reliable, accurate and appropriate outputs. Good prompts unlock significantly better performance without any change to the underlying model.
TechnicalFine-tuning
Fine-tuning is the process of further training a pre-trained model on a smaller, task-specific dataset so that it specialises in a particular domain, tone or set of behaviours. It sits between using a base model as-is and training a new model from scratch.
TechnicalLarge Language Model (LLM)
A Large Language Model (LLM) is a type of neural network trained on vast quantities of text to understand and generate human language. LLMs power chatbots, copilots, content generators and many modern AI features across consumer and business software.