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.
Related terms
Few-Shot Learning
Guiding a model by including a handful of examples in the prompt so it can follow the pattern.
Zero-Shot Learning
Asking a model to do a task with no examples, relying only on instructions and what it already knows.
Context Window
The maximum amount of text, measured in tokens, that a model can consider at once.
Prompt
The input you give a generative model, usually instructions or a question, that tells it what you want.