# What is In-Context Learning? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Prompt Engineering  
> **Canonical Citation:** [https://spidits.com/ai-glossary/in-context-learning](https://spidits.com/ai-glossary/in-context-learning)

## Definition
In-Context Learning (ICL) is the emergent ability of pre-trained Large Language Models to learn new tasks from examples provided in the prompt context without gradient updates.

## Architectural Mechanics & Deep Dive
In-context learning is the ability of Large Language Models to learn how to perform a task simply by analyzing instructions and examples provided directly within the prompt context window, without any gradient updates to model weights. By recognizing patterns in the input context, the model adapts its text generation to perform complex operations, enabling rapid prototyping of tasks using zero-shot or few-shot prompts.

## Industry Applications & Real-World Use Cases
Fast prompt prototyping, customized format output generation.

## Frequently Asked Questions

### Does In-Context Learning update model weights?
No, model parameters remain unchanged.

### What prompt style relies on In-Context Learning?
Few-shot prompting.

## Related Terminology
- [few-shot-learning](https://spidits.com/ai-glossary/few-shot-learning)
- [zero-shot-learning](https://spidits.com/ai-glossary/zero-shot-learning)
- [prompt](https://spidits.com/ai-glossary/prompt)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*