Towards a Catalog of Prompt Patterns to Enhance the Discipline of Prompt Engineering

ACM Sigada Ada Letters Pub Date : 2024-06-06 DOI:10.1145/3672359.3672364

Douglas C. Schmidt, Jesse Spencer-Smith, Quchen Fu, Jules White

引用次数: 1

Abstract

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.

查看原文本刊更多论文

建立提示模式目录，加强提示工程学科建设

大型语言模型（LLM）（如 ChatGPT 和 Claude）的迅速出现，正在彻底改变从教育、医疗到可靠软件系统工程等各个领域。这些 LLM 通过 "提示 "运行，"提示 "是用户用来查询和利用模型功能的自然语言输入。鉴于 LLMs 的新颖性，人们对如何有效使用提示语的了解主要还是基于孤立的使用案例。这种零散的方法限制了 LLM 的可靠性和实用性，尤其是在关键任务软件环境中应用 LLM 时。因此，要想在此类关键环境中充分发挥本地化语言工具的潜力，我们需要一种系统化、规范化的 "提示工程 "方法，以指导与这些本地化语言工具的互动和评估。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

ACM Sigada Ada Letters

自引率

0.00%

发文量