The increasing importance of process models highlights the demand for tools that enable an efficient and accurate transformation of natural language process descriptions into BPMN 2.0 process models. Despite significant advancements in natural language processing and large language models, automatically generating process models that are syntactically correct, semantically accurate, and pragmatically useful remains a challenge, particularly for individuals without deeper expertise in process modeling. To tackle this challenge, the authors have been developing BPMNGen, an LLM-based conversational framework, which leverages advanced natural language processing and large language models to automate the generation of BPMN 2.0 process models from natural language process descriptions. To evaluate the quality of the models generated with BPMNGen, two studies were conducted: one study focused on the semantic quality of the generated process models in relation to given process descriptions and another one assessed process model comprehensibility, including the cognitive load of the study participants when reading the LLM-generated models, their level of acceptability, and their performance. The results show that LLMs already perform well for simpler and moderately complex processes, while struggling with higher complexity – highlighting both current limitations and opportunities for further improving automated BPMN 2.0 model generation.
This paper presents a comprehensive literature review, focusing on the emerging intersection of chatbot technology and the generation of process models. As an evolving field of study, the integration of interactive chatbots into process model generation represents a promising approach, blending advancements in artificial intelligence in general, and natural language processing in particular, with process management methods. This review systematically examines the existing literature across multiple disciplines, identifying and analyzing studies that touch upon the individual components of this nascent topic: chatbot technology, process model generation, and their synergistic potential. Despite the scarcity of direct research aimed at using chatbots for process model generation, this review synthesizes relevant findings from related domains, such as natural language processing applications in process modeling, and the broader impact of chatbot interfaces in various domains. Through this analysis, we aim to map the current landscape of research, highlight significant gaps, and suggest potential pathways for future investigations. This paper not only aggregates existing knowledge, but also assesses the applicability and implications of current technologies and theories when generating process models with the assistance of interactive chatbots. The outcome is a foundational compendium for researchers and practitioners interested in exploring this innovative intersection, providing a springboard for future research and development in this promising area.