Wei, JasonWang, XuezhiSchuurmans, DaleBosma, MaartenIchter, BrianXia, FeiChi, EdLe, QuocZhou, Denny2025-06-022025-06-022022-01-10https://arxiv.org/abs/2201.11903http://data.inu.ac.kr/handle/123456789/1955Chain-of-Thought prompting 기법은 LLM의 다단계 추론 과정을 유도하여 복잡한 문제 해결력을 높이는 데 효과적임을 보입니다. ©2022 Google ResearchWe 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.en-USChain-of-ThoughtPrompt EngineeringReasoningLLMArticle