AI Dictionary › Prompting

In-Context Learning

In-context learning is a language model's ability to "learn" a task directly from the examples and instructions inside the prompt, with no weight retraining. The model adapts its behaviour using only what it reads at inference time. Example: in the prompt you write "Classify reviews. 'Great product' → positive. 'Slow delivery' → negative. 'The charger is broken' →" and the model completes with "negative," inferring the rule from the two examples. It is the mechanism behind few-shot and one-shot prompting: everything happens within the context window.

Definition

Use it when you want to specialise the model on a format or rule without fine-tuning: two to five well-chosen examples in the prompt are enough. Fast, cheap and reusable.

Related terms

• Few-shot
• One-shot
• Demonstration Selection
• Context Window
• Prompt Template

More in Prompting

• Prompt
• Prompting
• Role Assignment
• Zero-shot
• Few-shot
• Chain of Thought
• Prompt Engineering
• Output Format

Put it into practice

• Real scenario: apply this concept with an instant AI verdict.
• Daily gym: short drills to train dictionary concepts.
• Playoff game: challenge other players, elimination-style.

📱 Download the Android app (beta) iOS coming soon

Say what you mean. Get what you need.

Grace Certified, the AI coach that trains and certifies your prompt engineering, by Agora Intelligence.