Prompting & context · Glossary term
What is Few-Shot?
In-context learning that includes a small set of demonstrations before the target input so the model can infer the desired task, format, or decision boundary.
“Give the model a few examples in the prompt.”
Why does Few-Shot matter?
Example quality and coverage matter more than a universal example count. Poor or contradictory demonstrations can reduce reliability.
Learn Few-Shot in the course
Lessons that name Few-Shot in a title or section
- Few-Shot, Chain-of-Thought, Tree-of-Thought
Telling a model what to do is prompting. Showing it how to think is engineering. The gap between 78% and 91% accuracy on the same model, same task, same data is not a better model.
- Flamingo and Gated Cross-Attention for Few-Shot VLMs
DeepMind's Flamingo (2022) did two things before anyone else. It showed a single model could process arbitrarily interleaved sequences of images, videos, and text.
- Multilingual NLP
One model, 100+ languages, zero training data for most of them. Cross-lingual transfer is the practical miracle of the 2020s. English has billions of labeled examples. Urdu has thousands.
Covered in Phase 05: NLP: Foundations to Advanced, Phase 11: LLM Engineering and Phase 12: Multimodal AI.
Related terms
- Zero-ShotPerforming a task from instructions or task framing without including task-specific demonstrations in the immediate input.
- In-Context LearningA model adapting its behavior from instructions, examples, or patterns supplied in the current input without an ordinary parameter update.
- Prompt EngineeringDesigning model-facing instructions, examples, constraints, and output requirements to improve behavior on a defined task.
- Context WindowThe maximum token capacity available to one model inference under a specific model and API contract.
- Prompt SensitivityVariation in model output or measured performance caused by changes to prompt wording, order, formatting, or examples that preserve the…
More terms in Prompting & context
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.