Prompting & context · Glossary term
What is In-Context Learning?
A model adapting its behavior from instructions, examples, or patterns supplied in the current input without an ordinary parameter update.
Why does In-Context Learning matter?
It explains how one pretrained model can perform a new task from context while keeping its weights unchanged.
In-Context Learning in practice
Place representative demonstrations before the target input, test order and formatting variants, and keep evaluation examples separate from the demonstrations.
What is the common confusion about In-Context Learning?
In-context learning is temporary conditioning, not fine-tuning, durable memory, or proof that the model inferred the intended rule.
Learn In-Context Learning in the course
No lesson links to this term yet. Search the course catalog for it.
Related terms
- Few-ShotIn-context learning that includes a small set of demonstrations before the target input so the model can infer the desired task, format,…
- Zero-ShotPerforming a task from instructions or task framing without including task-specific demonstrations in the immediate input.
- Context WindowThe maximum token capacity available to one model inference under a specific model and API contract.
- Prompt EngineeringDesigning model-facing instructions, examples, constraints, and output requirements to improve behavior on a defined task.
Sources
More terms in Prompting & context
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.