Zero-shot and few-shot learning

Zero-shot and few-shot learning

The ability of a model to perform a task it was never explicitly trained on, either with no examples at all (zero-shot) or with only a handful of examples given in the prompt (few-shot). This flexibility is one of the most striking properties of large language models, which can often follow a new instruction format after seeing just one or two demonstrations. (See also: Prompt engineering, Large language model)