Towards Better Chain-of-Thought Prompting Strategies: A Survey
It provides a comprehensive reference for researchers and practitioners working with CoT prompting, but is incremental as it synthesizes existing research rather than introducing novel findings.
This survey tackles the lack of a systematic summary and guide for Chain-of-Thought (CoT) prompting in large language models by analyzing key factors influencing its effectiveness and providing application guidance, without presenting new experimental results or numbers.
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.