According to the original GPT-3 paper, "Language Models are Few-Shot Learners" (Brown et al., 2020), which best describes the difference between zero-shot and few-shot prompting?
- Zero-shot provides no task examples in the prompt, relying only on a natural language instruction, while few-shot includes a small number of input-output examples in the prompt before the actual query
- Zero-shot requires the model to be fine-tuned on the target task first, while few-shot requires no training at all
- Zero-shot and few-shot both require gradient updates to the model's weights; they differ only in how many examples are used per update
- Few-shot prompting means the model is shown zero examples but asked to solve the task in fewer than five reasoning steps
Correct answer: A. Zero-shot provides no task examples in the prompt, relying only on a natural language instruction, while few-shot includes a small number of input-output examples in the prompt before the actual query
In Brown et al. (2020), the zero-shot setting gives the model only a natural language description or instruction of the task with no worked examples, while the few-shot setting (in-context learning) includes several demonstration examples formatted as input-output pairs directly in the prompt before the real query, with no weight updates in either case. The second option is wrong because neither setting involves fine-tuning; the paper's central point is that GPT-3 performs tasks purely through prompting, without any gradient-based training on the target task. The third option is wrong because in-context learning explicitly does not update model weights at all -- the "learning" happens only within the context window at inference time, not through gradient updates. The fourth option confuses few-shot examples with reasoning steps, which is an unrelated chain-of-thought concept rather than the actual definition of few-shot prompting given in this paper.
Source: Brown et al., "Language Models are Few-Shot Learners" (2020), arXiv:2005.14165, Sections 1-2