Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

dc.contributor.authorWei, Jason
dc.contributor.authorWang, Xuezhi
dc.contributor.authorSchuurmans, Dale
dc.contributor.authorBosma, Maarten
dc.contributor.authorIchter, Brian
dc.contributor.authorXia, Fei
dc.contributor.authorChi, Ed
dc.contributor.authorLe, Quoc
dc.contributor.authorZhou, Denny
dc.date.accessioned2025-06-02T13:09:56Z
dc.date.available2025-06-02T13:09:56Z
dc.date.issued2022-01-10
dc.descriptionChain-of-Thought prompting 기법은 LLM의 다단계 추론 과정을 유도하여 복잡한 문제 해결력을 높이는 데 효과적임을 보입니다. ©2022 Google Research
dc.description.abstractWe explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.
dc.description.sponsorshipGoogle Research
dc.identifier.urihttps://arxiv.org/abs/2201.11903
dc.identifier.urihttp://data.inu.ac.kr/handle/123456789/1955
dc.language.isoen_US
dc.publisherarXiv
dc.subjectChain-of-Thought
dc.subjectPrompt Engineering
dc.subjectReasoning
dc.subjectLLM
dc.titleChain-of-Thought Prompting Elicits Reasoning in Large Language Models
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2201.11903v6.pdf
Size:
870.87 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
97 B
Format:
Item-specific license agreed to upon submission
Description: