首页|Towards a Catalog of Prompt Patterns to Enhance the Discipline of Prompt Engineering
Towards a Catalog of Prompt Patterns to Enhance the Discipline of Prompt Engineering
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
The rapid advent of Large Language Models (LLMs), such as ChatGPT and Claude, is revolutionizing various fields, from education and healthcare to the engineering of reliable software systems. These LLMs operate through "prompts," which are natural language inputs that users employ to query and leverage the models' capabilities. Given the novelty of LLMs, the understanding of how to effectively use prompts remains largely anecdotal, based on isolated use cases. This fragmented approach limits the reliability and utility of LLMs, especially when they are applied in mission-critical software environments. To harness the full potential of LLMs in such crucial contexts, therefore, we need a systematic, disciplined approach to "prompt engineering" that guides interactions with and evaluations of these LLMs. This paper provides several contributions to research on LLMs for reliable software systems. First, it provides a holistic perspective on the emerging discipline of prompt engineering. Second, it discusses the importance of codifying "prompt patterns" to provide a sound foundation for prompt engineering. Third, it provides examples of prompt patterns that improve human interaction with LLMs in the context of software engineering, as well as other domains. We conclude by summarizing ways in which prompt patterns play an essential role in providing the foundation for prompt engineering.
Douglas C. Schmidt、Jesse Spencer-Smith、Quchen Fu、Jules White
NETL
NSTL
