Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
by Google Brain · free · Last verified 2026-03-17
Introduced chain-of-thought prompting, a simple technique of providing exemplars with step-by-step reasoning traces in few-shot prompts. This approach dramatically improves LLM performance on arithmetic, commonsense, and symbolic reasoning tasks, with the effect emerging at approximately 100B parameters.
https://arxiv.org/abs/2201.11903 ↗A
A—Great
Adoption: A+Quality: A+Freshness: B+Citations: A+Engagement: F
Specifications
- License
- Open Access
- Pricing
- free
- Capabilities
- arithmetic-reasoning, commonsense-reasoning, symbolic-reasoning, multi-step-reasoning
- Integrations
- Use Cases
- mathematical-problem-solving, reasoning-tasks, prompt-engineering
- API Available
- No
- Tags
- chain-of-thought, reasoning, prompting, arithmetic, commonsense
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
82.1Adoption
97
Quality
95
Freshness
72
Citations
97
Engagement
0
Put AI to work for your business
Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.