What is the difference between few-shot and zero-shot prompting?
Reviewed by Jason Burns, Editorial Steward · Last updated
Zero-shot prompting asks the model to perform a task with only an instruction and no examples; few-shot prompting includes a handful of worked input–output examples inside the prompt to steer the model's behavior. As Tom B. Brown et al., put it on the record: "Scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches."
Source: arxiv.org/abs/2005.14165