# What is the Best Process Model Representation? A Comparative Analysis for Process Modeling with Large Language Models

arXiv: https://arxiv.org/abs/2507.11356 · HTML: https://mlsanity.com/paper/2507.11356/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [Large Language Models can accomplish Business Process Management Tasks](https://mlsanity.com/paper/2307.09923/) (2023)
- [Process Modeling With Large Language Models](https://mlsanity.com/paper/2403.07541/) (2024)
- [PET: An Annotated Dataset for Process Extraction from Natural Language Text](https://mlsanity.com/paper/2203.04860/) (2022)
- [Evaluating Large Language Models on Business Process Modeling: Framework, Benchmark, and Self-Improvement Analysis](https://mlsanity.com/paper/2412.00023/) (2024)
- [ProMoAI: Process Modeling with Generative AI](https://mlsanity.com/paper/2403.04327/) (2024)
- [Conversational Process Modeling: Can Generative AI Empower Domain Experts in Creating and Redesigning Process Models?](https://mlsanity.com/paper/2304.11065/) (2023)
- [Leveraging Generative AI for Extracting Process Models from Multimodal Documents](https://mlsanity.com/paper/2406.04959/) (2024)
- [Evaluating the Process Modeling Abilities of Large Language Models -- Preliminary Foundations and Results](https://mlsanity.com/paper/2503.13520/) (2025)

## Built on by (most cited first, 1 of 1)

- [Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design](https://mlsanity.com/paper/2607.06175/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly applied for Process Modeling (PMo) tasks such as Process Model Generation (PMG). To support these tasks, researchers have introduced a variety of Process Model Representations (PMRs) that serve as model abstractions or generation targets. However, these PMRs differ widely in structure, complexity, and usability, and have never been systematically compared. Moreover, recent PMG approaches rely on distinct evaluation strategies and generation techniques, making comparison difficult. This paper presents the first empirical study that evaluates multiple PMRs in the context of PMo with LLMs. We introduce the PMo Dataset, a new dataset containing 55 process descriptions paired with models in nine different PMRs. We evaluate PMRs along two dimensions: suitability for LLM-based PMo and performance on PMG. textitMermaid achieves the highest overall score across six PMo criteria, whereas textitBPMN text delivers the best PMG results in terms of process element similarity.