Prompt Orchestration Markup Language
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 86 references that are in the map. First posted on arXiv 19 Aug 2025.
Builds on
30 of 86 references.
References · 30
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2021Training Verifiers to Solve Math Word Problemscited by 10,109
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2021Evaluating Large Language Models Trained on Codecited by 8,320
- 2020Measuring Massive Multitask Language Understandingcited by 7,963
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
- 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
- 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
- 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
- 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
18 more
- 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
- 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
- 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
- 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 421
- 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
- 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 289
- 2024CodeGemma: Open Code Models Based on Gemmacited by 150
- 2024ProSA: Assessing and Understanding the Prompt Sensitivity of LLMscited by 149
- 2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 141
- 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
- 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 100
- 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 95
- 2023ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testingcited by 88
- 2022How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Modelscited by 44
- 2024Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimizationcited by 30
- 2024Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognitioncited by 16
- 2025Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimizationcited by 16
- 2025TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Modelscited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.