In-Context Learning

Entity Type: Glossary ID: in-context-learning

Definition: The ability of language models to learn and adapt to new tasks during inference by using examples or instructions provided in the input context, without updating model parameters. This enables flexible task performance without retraining.

Related Terms: - few-shot-learning - prompt-engineering - emergent-abilities - context-window

Source Urls: - https://en.wikipedia.org/wiki/Few-shot_learning#In-context_learning

Tags: - learning-paradigms - emergent-abilities - language-models

Status: active

Version: 1.0.0

Created At: 2025-08-31

Last Updated: 2025-08-31