用标记语言让复杂提示更结构化、易管理。
Prompt Orchestration Markup Language
- 用组件化标签定义角色、任务和示例，逻辑清晰
- 支持文档、表格、图像等多类型数据无缝集成
- 提供样式与内容分离的系统，适合团队协作开发
大型语言模型需要复杂的提示设计，但现有方法在结构化、数据整合、格式敏感性及工具支持方面存在不足。为解决这些问题，我们提出 POML（Prompt Orchestration Markup Language）。POML 采用组件化标记定义角色、任务与示例，使用专用标签实现多类型数据（文档、表格、图像）的无缝集成，并引入类似 CSS 的样式系统，实现内容与展示分离，降低格式敏感性。它还支持动态提示模板与完整的开发者工具链（包括 IDE 支持、SDK），提升版本控制与协作效率。通过两个案例研究验证其在复杂应用集成（PomLink）与准确率表现（TableQA）上的效果，并通过用户研究评估其在真实开发场景中的有效性。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。