Associate Professor
Technical University of Denmark
Formal modeling is essential for understanding, analyzing, and optimizing processes, yet formal techniques often pose a barrier for domain experts unfamiliar with them. This paper introduces BeePath, a framework designed to bridge this gap by allowing textual descriptions of business processes while maintaining formal guarantees. Unlike existing approaches that either eliminate ambiguities or impose rigid structures, BeePath leverages a constrained natural language to capture processes in a structured yet accessible manner. The framework also employs large language models (LLMs) to assist in converting unstructured descriptions into this structured format, which is then parsed into formal representations such as Petri nets, BPMN, and DECLARE. Our evaluation demonstrates BeePath’s effectiveness in capturing key process patterns and ensuring model consistency. By integrating natural language with formal process modeling, BeePath aims at enhancing accessibility for domain experts, fostering a more intuitive and democratized approach to business process management.
In Proceedings of NLP4BPM (BPM Workshop); Toronto, Canada; September 27-October 2 2026.
Copyright and moral rights for the publications made accessible in the public website are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.
If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.
Latest website update: 02 October 2026.