Towards LLM-Powered Consistency in Model-Based Low-Code Platforms
Gespeichert in:
| Titel: | Towards LLM-Powered Consistency in Model-Based Low-Code Platforms |
|---|---|
| Autoren: | Hagel, Nathan, Hili, Nicolas, Bartel, Alexander, Koziolek, Anne |
| Quelle: | 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C). :364-369 |
| Verlagsinformationen: | IEEE, 2025. |
| Publikationsjahr: | 2025 |
| Schlagwörter: | ddc:004, LLM, DSL, low-code development platform, consistency, AI, model-driven engineering, DATA processing & computer science, meta-model |
| Beschreibung: | Low-code platforms often use various models that define the application built by citizen developers. With the increasing size and complexity of the applications built using low-code platforms, the number of required models and the dependencies between them expand. However, with increased complexity, keeping these models consistent during the development or evolution of the application is crucial and often a non-trivial task for citizen developers. In this paper, we present four approaches to how LLMs can be used and integrated on the architecture level into low-code platforms to (i) create consistent models automatically, (ii) keep models consistent based on different types of dependencies, and (iii) support users in maintaining consistent models during the development. We implemented the approaches in a prototype and evaluated them in an exploratory study. The results show that state-of-the-art LLMs are capable of preserving consistency for low-code models as well as generating correct and consistent models in various scenarios. |
| Publikationsart: | Article Conference object |
| Dateibeschreibung: | application/pdf |
| DOI: | 10.1109/icsa-c65153.2025.00058 |
| DOI: | 10.5445/ir/1000180779 |
| Zugangs-URL: | https://publikationen.bibliothek.kit.edu/1000180779 https://doi.org/10.5445/IR/1000180779 https://publikationen.bibliothek.kit.edu/1000180779/158661758 |
| Rights: | STM Policy #29 |
| Dokumentencode: | edsair.doi.dedup.....f7526f46a5ff9741d3a93329ec0772c1 |
| Datenbank: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | Low-code platforms often use various models that define the application built by citizen developers. With the increasing size and complexity of the applications built using low-code platforms, the number of required models and the dependencies between them expand. However, with increased complexity, keeping these models consistent during the development or evolution of the application is crucial and often a non-trivial task for citizen developers. In this paper, we present four approaches to how LLMs can be used and integrated on the architecture level into low-code platforms to (i) create consistent models automatically, (ii) keep models consistent based on different types of dependencies, and (iii) support users in maintaining consistent models during the development. We implemented the approaches in a prototype and evaluated them in an exploratory study. The results show that state-of-the-art LLMs are capable of preserving consistency for low-code models as well as generating correct and consistent models in various scenarios. |
|---|---|
| DOI: | 10.1109/icsa-c65153.2025.00058 |