Back to GlossaryCore Concepts

Zero-Shot Learning

Definition

The ability of a model to perform a task it has never been explicitly trained on, without any task-specific examples provided.

Zero-shot learning represents one of the most remarkable capabilities of large AI models. A model performs a task based solely on its general knowledge and the task description, without seeing any examples. For instance, a large language model can translate between languages it wasn't specifically trained to translate by understanding the concept of translation from its training data. Zero-shot capabilities scale with model size and the diversity of pre-training data. GPT-3 demonstrated strong zero-shot performance across many tasks, and subsequent models have continued to improve. Zero-shot learning is a key measure of how well a model generalizes.

Companies in Core Concepts

View Core Concepts companies →