Szczegóły publikacji
Opis bibliograficzny
Revisiting BPMN assignments with AI in mind: insights from experiments with large language models in process modeling education / Krzysztof KLUZA, Marzena Grzesiak, Piotr Sliż, Leszek Szała, Anna Suchenia, Karol Suchenia, Marek Moszyński // W: Business Process Management : Responsible BPM Forum, Process Technology Forum, Educators Forum : BPM 2025 RBPM, PT, and Educators Forum Seville, Spain, August 31 – September 5, 2025 : proceedings / eds. Mahendrawathi Er, [et al.]. — Cham : Springer Nature, cop. 2026. — (Lecture Notes in Business Information Processing ; ISSN 1865-1348 ; LNBIP 565). — ISBN: 978-3-032-02935-5; e-ISBN: 978-3-032-02936-2. — S. 358–372. — Bibliogr., Abstr. — Publikacja dostępna online od: 2025-08-30
Autorzy (7)
- AGHKluza Krzysztof
- Grzesiak Marzena
- Sliż Piotr
- Szała Leszek
- Suchenia Anna
- Suchenia Karol
- Moszyński Marek
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 162196 |
|---|---|
| Data dodania do BaDAP | 2025-09-10 |
| DOI | 10.1007/978-3-032-02936-2_25 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference in Business Process Management 2025 |
| Czasopismo/seria | Lecture Notes in Business Information Processing |
Abstract
As Large Language Models (LLMs) become increasingly available to students, BPM educators face a new challenge: how to design assignments that remain pedagogically effective and resistant to superficial AI-generated answers. This paper presents the results of two experiments that simulate common BPMN-related homework tasks and test how LLMs respond to them. The first experiment focused on answering comprehension questions based on five BPMN models, each provided either in PNG or XML format. The second asked the models to detect modeling errors in 30 flawed BPMN diagrams. In both cases, we evaluated the outputs of ChatGPT-4o and Gemini Flash, analyzing the correctness, reasoning, and completeness of their responses. Our findings show that while current LLMs are not yet fully capable of reliably solving BPMN assignments—especially those involving deeper process logic—they can already provide partially correct and plausible responses. This raises questions about the future of BPM education, the design of AI-aware assignments, and the role of LLMs as potential learning assistants. Alongside insights and lessons learned, we provide materials to help instructors adapt their teaching to an AI-enabled environment.
