← Lessons

quiz vs the machine

Gold1500

Machine Learning

In Context Learning From Prompts

Steering a large model with examples in the prompt instead of new weights.

5 min read · core · beat Gold to climb

A new way to adapt

Traditionally you adapt a model by fine tuning its weights on a labeled set. Large language models opened another route: in context learning, where you simply place a few worked examples in the prompt and the model infers the pattern, updating no weights at all.

Zero, one, and few shot

The number of examples in the prompt names the setting:

  • Zero shot gives only an instruction and no examples
  • One shot includes a single demonstration
  • Few shot includes several demonstrations of input and desired output

From these examples the model picks up the format, the task, and the style, then applies them to a new query. It is learning during inference, drawing on patterns absorbed in pretraining.

Strengths and limits

In context learning needs no training run and adapts instantly, which is ideal for quick tasks. But it is limited by the context window, sensitive to example order and wording, and usually less reliable than true fine tuning for hard, high volume tasks.

Key idea

Few shot in context learning adapts a model by showing examples in the prompt rather than changing weights, trading instant flexibility for context limits and prompt sensitivity.

Check yourself

Answer to earn rating on the learn ladder.

1. What changes in the model during in context learning?

2. A key limitation of few shot prompting is?