Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2023

Abstract

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 reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zeroshot-CoT concatenates the target problem statement with “Let’s think step by step” as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation errors, missing-step errors, and semantic misunderstanding errors. To address the missing-step errors, we propose Planand-Solve (PS) Prompting. It consists of two components: first, devising a plan to divide the entire task into smaller subtasks, and then carrying out the subtasks according to the plan. To address the calculation errors and improve the quality of generated reasoning steps, we extend PS prompting with more detailed instructions and derive PS+ prompting. We evaluate our proposed prompting strategy on ten datasets across three reasoning problems. The experimental results over GPT-3 show that our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem. The code can be found at https://github.com/AGIEdgerunners/Plan-and-Solve-Prompting.

Keywords

Calculation error, Language model, Large margins, Multisteps, Performance, Reasoning problems

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems | Programming Languages and Compilers

Research Areas

Data Science and Engineering

Publication

61st Annual Meeting of the Association for Computational Linguistics, ACL 2023: Toronto, July 9-14: Proceedings

First Page

2609

Last Page

2634

ISBN

9781959429722

Identifier

10.18653/v1/2023.acl-long.147

Publisher

ACL

City or Country

Toronto

Copyright Owner and License

Publisher

Additional URL

https://doi.org/10.18653/v1/2023.acl-long.147

Share

COinS