{"version":"1.0","type":"rich","provider_name":"gaks.ai AI Glossary","provider_url":"https://gaks.ai/glossary","title":"Zero-Shot Learning — AI Glossary","author_name":"Glenn Katrud Solheim","author_url":"https://gaks.ai","width":600,"height":200,"html":"

AI Glossary — gaks.ai

Zero-Shot Learning

The ability of a model to perform a task it has never explicitly been trained on, with no examples provided at inference time. Large language models exhibit impressive zero-shot capabilities, you can ask them to perform tasks simply by describing what you want, without any demonstrations, though performance is generally better with at least a few examples. See also: few-shot learning, in-context learning.

Source: gaks.ai/glossary/zero-shot-learning →
"}