Chain of Thought

Chain of thought (CoT) prompting encourages the model to think through a problem step by step before giving a final answer. Adding "think step by step" or "show your reasoning" to a prompt activates this behavior. The model writes out intermediate reasoning steps, which improves accuracy on complex tasks.

CoT is one of the simplest and most effective prompting techniques. It measurably improves performance on math, logic, coding, and reasoning tasks. It costs nothing to use - just add a few words to your prompt. It is especially valuable for complex problems where the model might jump to a wrong answer without explicit reasoning.

Wei et al., "Chain-of-Thought Prompting" - https://arxiv.org/abs/2201.11903

Google AI Blog: "Language Models Perform Reasoning" - https://ai.googleblog.com/2022/05/language-models-perform-reasoning-via.html