Back to GlossaryCore Concepts

Few-Shot Learning

Definition

The ability of an AI model to learn and generalize from only a handful of examples, rather than requiring thousands or millions of training samples.

Few-shot learning enables models to adapt to new tasks with very limited data. In the context of large language models, few-shot learning refers to providing a small number of examples in the prompt to guide the model's behavior (also called in-context learning). For example, showing a model three examples of sentiment classification allows it to classify new text without any weight updates. This capability emerged as models scaled up in size and training data. Few-shot learning is closely related to meta-learning, where models learn how to learn efficiently. It is especially valuable in domains where labeled data is scarce or expensive to obtain.

Companies in Core Concepts

View Core Concepts companies →