提示编排标记语言

摘要

大型语言模型（LLMs）需要复杂的提示工程，然而当前实践在结构、数据整合、格式敏感性和工具支持方面面临挑战。现有方法缺乏全面解决方案，无法有效组织涉及多种数据类型（文档、表格、图像）的复杂提示，或系统化管理呈现方式的多样性。为填补这些空白，我们引入了POML（提示编排标记语言）。POML采用基于组件的标记来实现逻辑结构（角色、任务、示例），使用专用标签实现无缝数据整合，并采用类似CSS的样式系统将内容与呈现分离，降低格式敏感性。它包含动态提示模板和全面的开发者工具包（IDE支持、SDK），以提升版本控制和协作效率。我们通过两个案例研究验证了POML在复杂应用集成（PomLink）和准确性表现（TableQA）方面的影响，并通过用户研究评估了其在现实开发场景中的有效性。

English

Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to decouple content from presentation, reducing formatting sensitivity. It includes templating for dynamic prompts and a comprehensive developer toolkit (IDE support, SDKs) to improve version control and collaboration. We validate POML through two case studies demonstrating its impact on complex application integration (PomLink) and accuracy performance (TableQA), as well as a user study assessing its effectiveness in real-world development scenarios.