cs.CLNov 13, 2026

A Multi-Layered AI Pipeline for BPMN Generation from Natural Language

Authors: Alexandru Rancea, Ionut Anghel, Tudor Cioara, Ovidiu Anchidin, Ancuta Nemes

Organizations: Computer Science Department, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, Romania. · Niculae Stancioiu Heart Institute, Calea Motilor 19-21, 400001 Cluj-Napoca, Romania.

Abstract

The automated transformation of unstructured natural language process descriptions into Business Process Model and Notation (BPMN) diagrams remains a challenging task, due to linguistic ambiguity and the difficulty to detect non-adjacent control-flow relationships. This paper proposes a solution for generating BPMN models from natural language descriptions through a multi-layered pipeline that integrates transformer-based architectures, Large Language Models and ontology population. The proposed method starts with natural language descriptions and separates textual processing, control-flow relation extraction, and structural validation into dedicated components. Entity extraction is performed using a fine-tuned RoBERTa-based transformer model while a control-flow engine captures non-adjacent relationships through LLM-based inference. To improve generalization under limited available data, the approach uses a dynamic few-shot strategy with con- trolled template input construction, enabling improved generalization under limited data availability. Additionally, an ontology population mechanism is introduced to represent the generated process models as semantic knowledge structures. For evaluation purposes we have used from the literature and industry reference processes. Additionally, we have validated the proposed method on a real-world heart disease patients transitional care process, capturing practical constraints and multi-actor collaboration, and serving as an expert-defined benchmark scenario. Experimental results demonstrate strong performance in the relation extraction task, achieving an accuracy of 90.7%, as well as maintaining structural alignment between the generated and reference BPMN models across multiple evaluation scenarios scenarios.

Explore similar work

CardsList
  1. Large Language Models to Enhance Business Process Modeling: Past, Present, and Future Trends

    Apr 15, 2026João Bettencourt, Sérgio GuerreiroBusiness Process Modeling

  2. Instruction-Tuning Open-Weight Language Models for BPMN Model Generation

    Dec 12, 2025Gökberk Çelikmasat, Atay Özgövde, Fatma Başak AydemirBusiness Process ModelingOpen-Weight Language Models

  3. Automatic Generation of Executable BPMN Models from Medical Guidelines

    Apr 9, 2026Praveen Kumar Menaka Sekar, Ion Matei, Maksym Zhenirovskyy +4Business Process ModelingBusiness Process Automation