---
title: "In-context Learning"
description: "In-Context Learning (ICL) is a capability of Large Language Models (LLMs) to learn and perform tasks based solely on the context provided within a Prompt, without updating the model's parameters. By presenting examples or instructions within the input, LLMs can adapt to new tasks temporarily, enabling few-shot learning where the model generalizes from limited data. This emergent property of LLMs contrasts with traditional training methods that require parameter adjustments and extensive datasets."
canonical_url: "https://promptmetheus.com/resources/llm-knowledge-base/in-context-learning-icl"
---

> Index of every page on this site: [llms.txt](https://promptmetheus.com/llms.txt)

In-Context Learning (ICL) is a capability of [Large Language Models (LLMs)](https://promptmetheus.com/resources/llm-knowledge-base/large-language-model-llm) to learn and perform tasks based solely on the [context](https://promptmetheus.com/resources/llm-knowledge-base/context) provided within a [Prompt](https://promptmetheus.com/resources/llm-knowledge-base/prompt), without updating the model's parameters. By presenting examples or instructions within the input, LLMs can adapt to new tasks temporarily, enabling few-shot learning where the model generalizes from limited data. This emergent property of LLMs contrasts with traditional training methods that require parameter adjustments and extensive datasets.

## Sitemap

See the full [sitemap](https://promptmetheus.com/sitemap.md) for all pages.