[论文解读] The Prompt Canvas: A Literature-Based Practitioner Guide for Creating Effective Prompts in Large Language Models

Michael Hewing, Vincent Leinhos|arXiv (Cornell University)|Dec 6, 2024

Educational Tools and Methods被引用 5

一句话总结

论文介绍了 Prompt Canvas，一种基于画布的框架，通过系统性文献综述整合现有的提示工程技术，以引导从业者为大型语言模型设计有效的提示。

ABSTRACT

The rise of large language models (LLMs) has highlighted the importance of prompt engineering as a crucial technique for optimizing model outputs. While experimentation with various prompting methods, such as Few-shot, Chain-of-Thought, and role-based techniques, has yielded promising results, these advancements remain fragmented across academic papers, blog posts and anecdotal experimentation. The lack of a single, unified resource to consolidate the field's knowledge impedes the progress of both research and practical application. This paper argues for the creation of an overarching framework that synthesizes existing methodologies into a cohesive overview for practitioners. Using a design-based research approach, we present the Prompt Canvas, a structured framework resulting from an extensive literature review on prompt engineering that captures current knowledge and expertise. By combining the conceptual foundations and practical strategies identified in prompt engineering, the Prompt Canvas provides a practical approach for leveraging the potential of Large Language Models. It is primarily designed as a learning resource for pupils, students and employees, offering a structured introduction to prompt engineering. This work aims to contribute to the growing discourse on prompt engineering by establishing a unified methodology for researchers and providing guidance for practitioners.

研究动机与目标

• 将关于提示工程的分散知识整合成一个连贯的框架。
• 为从业者（学生、员工等）提供面向实践的学习资源。
• 通过建立统一的 prompting 方法论，为研究人员提供参考。

提出的方法

• 按照 SLR 和 PRISMA 启发步骤，对提示工程技术进行系统性文献综述。
• 将文献中的发现映射到可视化画布上，以提高可访问性和适用性。
• 定义一个四类画布结构（Persona/Role，Goal/Step-by-Step，Context/References，Format/Tonality）来组织提示要素。
• 回顾并整合关键提示技术，如 Few-shot、Chain-of-Thought，以及基于角色的提示，并结合文献中的支持性模式与技能。

实验结果

研究问题

• RQ1 提示工程技术，尤其是文本到文本模态的当前状态是什么？
• RQ2 如何将关于提示的零散知识整合成便于从业者使用的框架？
• RQ3 文献中应包含哪些要素和模式，以构成一个连贯的提示画布？

主要发现

• 提出一个统一的画布，用于可视化地组织提示工程技术，以便实践使用。
• 文献综述识别并综合多种提示技术和模式，纳入 Prompt Canvas 框架。
• 对提示的维度性视角包括交互、情境和结果，Chain-of-Thought 被强调为强大的推理技术。
• 从现有分类法中提取七到九个维度及相关元维度，以构建高效提示的结构。