Current approaches show strong potential, but they still act more as intelligent assistants than as fully autonomous process modelers, including the continued need for human involvement and the output quality.
Abstract
The automated generation of business process models from natural language descriptions has recently attracted growing attention at the intersection of Business Process Management (BPM), Natural Language Processing (NLP), and Large Language Models (LLMs). This paper presents a Systematic Literature Review (SLR) on the current state of research in this emerging field. Following the guidelines of Kitchenham et al. and the PRISMA framework, 29 studies published between January 1st, 2023 and March 10th, 2026 were identified, selected, and analyzed. The review addresses two research questions focusing on the applied methodological approaches, the used LLMs, the employed modeling languages, as well as the evaluation strategies, challenges, and limitations reported in the literature. The results show a clear shift from traditional NLP-based techniques toward LLM-only and hybrid approaches. OpenAI’s GPT family, especially GPT-4 and its variants, dominates the field, while BPMN is by far the most frequently used target process modeling language. Furthermore, existing studies evaluate automated process model generation primarily through output-focused methods, such as quantitative metrics, expert reviews, and comparisons with alternative or human-created process models. At the same time, the reviewed studies reveal important challenges, including the continued need for human involvement and the output quality. Overall, current approaches show strong potential, but they still act more as intelligent assistants than as fully autonomous process modelers.
The results show that the applied LLM can reliably detect structural and semantic differences between formal business process models using Business Process Model and Notation, while distinguishing them from acceptable variations, demonstrating strong potential for automated model validation.
Christian Bennoit, S. Zamani, Tobias Greff· Process Science· 0 citations
This survey provides the first systematic synthesis of LLM-based diagram modelling research, highlighting needs for standardised benchmarks, stronger evaluation protocols, broader diagram coverage, and techniques for improving semantic reliability and multi-view consistency.
The proposed model aims to support the formalization of model selection processes, improve decision-making, and enhance the traceability and transparency of LLMOps practices and forms part of a broader research effort toward the formalization of the entire LLMOps life cycle.
M. Chernigovskaya, A. Nahhas, Christian Haertel et al.· International Conference on...· 0 citations
It is argued that edge (sequence flow) generation is the weakest link once nodes are fixed, and typical structural failure modes (dangling nodes, disconnects, gateway violations, etc.) and causes tied to autoregressive generation are summarized.
Gennady G. Bulgakov, S. Yarushev· SOFT MEASUREMENTS AND COMPUT...· 0 citations
Nowadays, organisations face a high volume of business processes (BPs) along with numerous process features. In the current situation, the problems related to processing information, such as higher dimensionality, complexity, changeability, and scalability issues, have created significant challenges for business process improvement (BPI) and process mining (PM) approaches. This paper contributes in two ways. At first, for the first time, a systematic literature review of the challenges of the two main approaches, including BPI and PM, is presented. These challenges are in accordance with the problems associated with the high volume of BPs in organisations. Second, this paper proposes a new model of applying data mining to improve BPs, supporting the two mentioned approaches and reducing the related challenges. To assess the applicability of the proposed model, an actual BP dataset was used in this work. In the end, the advantages of the proposed model over the BPI methodologies and PM approach have been established. The proposed model can significantly alleviate the challenges associated with organisations’ high volume of BPs. Of course, it is crucial to carefully consider and manage inherent limitations to better implement the proposed model. In addition, the literature review can reveal a broader issue for other researchers to investigate related topics. These topics are elaborated on in various parts of this paper, particularly in the section related to challenges and solutions in BPI and PM. Furthermore, practitioners can also consider the main issues discussed in this literature review to improve BPs in their organisations.
Mohammad Khanbabaei, Abolfazl Karimi Sardari· Journal of Information &...· 0 citations
The use of large language models (LLMs) to support non-modeling experts of multi-perspective EM are investigated and LLMs can be seen as assistive technology for certain tasks in EM.
Peter-Alexander Kolev, H. Pruss, J. Wilken et al.· Journal of Software and Syst...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
