Towards Better Chain-of-Thought Prompting Strategies: A Survey

TL;DR

This survey comprehensively reviews recent research on Chain-of-Thought prompting for large language models, analyzing key factors influencing its effectiveness and providing guidance for better application and future directions.

Contribution

It offers a systematic analysis of factors affecting CoT prompting and serves as a comprehensive reference for researchers and practitioners.

Findings

Identifies key factors influencing CoT prompting effectiveness

Provides guidelines for applying CoT prompting in various tasks

Discusses challenges and future research directions

Abstract

Chain-of-Thought (CoT), a step-wise and coherent reasoning chain, shows its impressive strength when used as a prompting strategy for large language models (LLM). Recent years, the prominent effect of CoT prompting has attracted emerging research. However, there still lacks of a systematic summary about key factors of CoT prompting and comprehensive guide for prompts utilizing. For a deeper understanding about CoT prompting, we survey on a wide range of current research, presenting a systematic and comprehensive analysis on several factors that may influence the effect of CoT prompting, and introduce how to better apply it in different applications under these discussions. We further analyze the challenges and propose some future directions about CoT prompting. This survey could provide an overall reference on related research.