Automated BPMN Model Generation from Textual Process Descriptions: A Multi-Stage LLM-Driven Approach

TL;DR

This paper introduces a scalable, multi-stage LLM-driven pipeline for automatically generating and validating BPMN models from natural language descriptions, addressing heterogeneity and multilingual challenges.

Contribution

It presents a novel multi-stage process combining translation, validation, correction, and similarity assessment to reconstruct executable BPMN diagrams from text.

Findings

Generated 387 validated ground-truth models from 750 diagrams.

Achieved average reconstruction similarity above 0.75.

Approximately 50 near-perfect reconstructions with minor variations.

Abstract

Automatically reconstructing BPMN models from unstructured natural-language descriptions remains challenging due to heterogeneous modeling conventions, multilingual sources, and the lack of reliable ground truth. We present a scalable, multi-stage LLM-driven pipeline that automates both ground-truth construction and model reconstruction. Multilingual BPMN XML files are translated into English, validated using execution-oriented compliance checks in SpiffWorkflow, and iteratively repaired through targeted LLM-guided corrections to produce a consistent ground-truth corpus. From these validated models, process descriptions are generated and used to reconstruct executable BPMN~2.0 XML diagrams without manual curation. We introduce a multi-dimensional similarity framework combining structural metrics, type-distribution alignment, and embedding-based semantic measures. In an empirical study of 750 public BPMN diagrams, the pipeline generated 387 validated ground-truth models and achieved average reconstruction similarity above 0.75, including approximately 50 near-perfect reconstructions differing only in minor naming variations. The results demonstrate that LLMs can generate structurally compliant and semantically meaningful BPMN diagrams at scale.