Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models

• Main Authors: WANG, Lei, XU, Wanyu, LAN, Yihuai, HU, Zhiqiang, LAN, Yunshi, LEE, Roy Ka-Wei, LIM, Ee-peng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Calculation error; Language model; Large margins; Multisteps; Performance; Reasoning problems; Artificial Intelligence and Robotics; Databases and Information Systems; Programming Languages and Compilers
• Online Access: https://ink.library.smu.edu.sg/sis_research/8054; https://ink.library.smu.edu.sg/context/sis_research/article/9057/viewcontent/2023.acl_long.147.pdf
• Institution: Singapore Management University

Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate...