# In-context learning

**Source:** https://promtable.com/glossary/in-context-learning

> In-context learning is when a language model adapts its behaviour from examples shown in the prompt — no weights change, no fine-tuning.

---
In-context learning is when a language model adapts its behaviour from examples shown in the prompt — no weights change, no fine-tuning.

In-context learning (ICL) is the foundation of every prompting technique that supplies demonstrations. Few-shot prompting is the most common form. The model uses the examples as a soft specification of the task and generalises from them at inference time. ICL works because pretrained models have learned to model the underlying distribution well enough that a handful of examples shifts their behaviour meaningfully. Long-context models (Gemini 2 Pro, Claude with long context) now support 'many-shot' ICL — hundreds of examples — which can approach fine-tune quality for narrow tasks without changing weights.

## When to use

- Steering tone, format, or domain-specific style.
- When you cannot fine-tune (closed model, low data).
- Tasks with edge cases that zero-shot keeps missing.

## Common mistakes

- Using non-representative examples.
- Forgetting that ICL is sensitive to example ORDER, not just content.

## Related terms

- [few-shot-prompting](https://promtable.com/glossary/few-shot-prompting)
- [zero-shot-prompting](https://promtable.com/glossary/zero-shot-prompting)
- [system-prompt](https://promtable.com/glossary/system-prompt)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/in-context-learning
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/in-context-learning".
Contact: info@vibecodingturkey.com.