Chain-of-thought

Chain-of-thought (CoT) prompting encourages language models to reason step-by-step before producing a final answer, improving accuracy on multi-step arithmetic, logical reasoning, and coding tasks. CoT can be elicited by including worked examples in the prompt (few-shot CoT) or by simply appending "Let's think step by step" (zero-shot CoT).

The intermediate reasoning steps help the model avoid shortcut errors.