Chain-of-thought prompting elicits reasoning in LLMs
Wei et al. showed that prompting large models to write out intermediate reasoning steps dramatically improves performance on math and logic tasks — an ability that emerges with scale.
Key facts
- arXiv 2201.11903 (January 2022); NeurIPS 2022
- PaLM 540B with chain-of-thought reached state of the art on GSM8K math word problems at the time
- Follow-up: 'Let's think step by step' zero-shot CoT (Kojima et al., 2022)
- Precursor to trained reasoning models like OpenAI o1
What happened
Adding worked examples with step-by-step reasoning in the prompt caused large models to reason explicitly before answering.
Why it matters
Made 'thinking out loud' central to LLM capability; RL-trained reasoning models (o1, R1, Claude extended thinking) are its descendants.
Changelog
- 2026-09-29: created
Related events
Sources (2)
- paperChain-of-Thought Prompting Elicits Reasoning in Large Language Models (arXiv)
- officialLanguage Models Perform Reasoning via Chain of Thought (Google Research blog)
id: 2022-01-28-chain-of-thought · updated 2026-09-29 · open in the interactive timeline