Glossary Context Management 1 min read

Few-Shot Learning

Also known as: Few-Shot, In-Context Learning, k-Shot Learning

A machine learning approach where models learn to perform tasks from only a small number of examples, typically provided within the prompt or during a brief adaptation phase.

In-context learning, k-shot, one-shot learning, zero-shot learning, few-shot prompting, learning from examples, meta-learning, prompt examples, demonstration learning, sample efficiency, low-resource learning

Sources & References

1
Language Models are Few-Shot Learners (GPT-3)

OpenAI

Research
2
A Survey on In-Context Learning

arXiv

Research
3
Few-Shot Prompting - OpenAI Cookbook

OpenAI

Documentation

Related Terms

Context Window

The maximum amount of text (measured in tokens) that a large language model can process in a single interaction, encompassing both the input prompt and the generated output. Managing context windows effectively is critical for enterprise AI deployments where complex queries require extensive background information.

Large Language Model

A type of AI model trained on vast amounts of text data that can understand, generate, and manipulate human language, typically based on the transformer architecture with billions of parameters.

Machine Learning

A subset of artificial intelligence that enables systems to learn and improve from experience without being explicitly programmed, using algorithms that identify patterns in data.

Prompt Engineering

The practice of designing, optimizing, and structuring inputs (prompts) to AI language models to elicit desired outputs, including techniques for instruction formatting, context provision, and output specification.
Previous Federated Context Authority
Next Fine-Tuning
Back to Glossary