Prompting & Inference

In-Context Learning

A model’s ability to learn a task from examples placed in the prompt, without any change to its weights.

In-context learning is the striking ability of large language models to pick up a new pattern purely from what you put in the prompt, then apply it immediately, all without retraining. It is what makes few-shot prompting work. The models weights never change during this, the adaptation lives entirely in the current context and vanishes when the conversation ends.