BPMN Assistant: An LLM-Based Approach to Business Process Modeling
This addresses the problem of manual and error-prone business process modeling for domain experts, though it is incremental as it builds on existing LLM and BPMN techniques.
The paper tackles automating business process modeling by developing BPMN Assistant, a tool that uses Large Language Models to create and edit BPMN diagrams from natural language, with results showing JSON representation improves reliability, speed, and editing success rates compared to XML.
This paper presents BPMN Assistant, a tool that leverages Large Language Models (LLMs) for natural language-based creation and editing of BPMN diagrams. A specialized JSON-based representation is introduced as a structured alternative to the direct handling of XML to enhance the accuracy of process modifications. Process generation quality is evaluated using Graph Edit Distance (GED) and Relative Graph Edit Distance (RGED), while editing performance is evaluated with a binary success metric. Results show that JSON and XML achieve similar similarity scores in generation, but JSON offers greater reliability, faster processing, and significantly higher editing success rates. We discuss key trade-offs, limitations, and future improvements. The implementation is available at https://github.com/jtlicardo/bpmn-assistant.