Chain-of-Thought Prompting (2022) › 2022: Chain-of-Thought Prompting
History of Language AIAll chapters Chain-of-Thought Prompting (2022) › 2022: Chain-of-Thought PromptingOne section · Sections in this chapter1 / 7 ↓
Reading tools Definitions & inline links
Choose your expertise level to adjust how many terms are explained. Beginners see more tooltips, experts see fewer to maintain reading flow. Hover over underlined terms for instant definitions.
Article links
Make inline references clickable
In 2022, researchers at Google introduced chain-of-thought prompting, a technique that improved language models' ability to solve complex reasoning problems. Developed by Jason Wei and colleagues, it demonstrated that prompting models to generate intermediate reasoning steps before arriving at an answer could elicit capabilities that seemed absent when models jumped directly to final answers. The result showed that prompting itself could provide reasoning instructions and that large language models required explicit scaffolding to display some latent reasoning abilities.
In 2022, models like GPT-3 and PaLM performed well on many tasks through few-shot learning. However, these models struggled with multi-step reasoning problems that required breaking down complex questions into intermediate steps. Mathematical word problems, logical puzzles, and complex planning tasks often resulted in incorrect answers, even when the models had sufficient knowledge to solve them. Researchers observed that models could sometimes produce correct answers but failed more often than expected on problems that humans would solve by working through intermediate steps.
At the same time, the field was beginning to understand that how prompts were structured could significantly influence model behavior. Few-shot learning had shown that providing examples in prompts could guide models toward desired behaviors. The chain-of-thought insight extended this principle by recognizing that the structure of those examples, specifically whether they showed intermediate reasoning steps, could activate fundamentally different model capabilities. This realization bridged the gap between what models could theoretically do and what they demonstrated in practice.
The development of chain-of-thought prompting built on existing prompting techniques but introduced one change: explicitly encouraging models to generate reasoning chains. Rather than asking models to produce direct answers, chain-of-thought prompting provided examples that showed step-by-step reasoning, teaching models to decompose problems and work through solutions methodically. This approach revealed that reasoning capability existed within large language models but needed to be activated through appropriate prompting strategies.