Open Access

ARTICLE

A Novel Unified Framework for Automated Generation and Multimodal Validation of UML Diagrams

Van-Viet Nguyen¹, Huu-Khanh Nguyen², Kim-Son Nguyen¹, Thi Minh-Hue Luong¹, Duc-Quang Vu¹, Trung-Nghia Phung³, The-Vinh Nguyen^1,*

1 Faculty of Information Technology, Thai Nguyen University of Information and Communication Technology, Thai Nguyen, 250000, Viet Nam
2 Distance Learning Center, Thai Nguyen University, Thai Nguyen, 250000, Viet Nam
3 Faculty of Arts and Communications, Thai Nguyen University of Information and Communication Technology, Thai Nguyen, 250000, Viet Nam

* Corresponding Author: The-Vinh Nguyen. Email:

Computer Modeling in Engineering & Sciences 2026, 146(1), 33 https://doi.org/10.32604/cmes.2025.075442

Received 31 October 2025; Accepted 18 December 2025; Issue published 29 January 2026

Abstract

It remains difficult to automate the creation and validation of Unified Modeling Language (UML) diagrams due to unstructured requirements, limited automated pipelines, and the lack of reliable evaluation methods. This study introduces a cohesive architecture that amalgamates requirement development, UML synthesis, and multimodal validation. First, LLaMA-3.2-1B-Instruct was utilized to generate user-focused requirements. Then, DeepSeek-R1-Distill-Qwen-32B applies its reasoning skills to transform these requirements into PlantUML code. Using this dual-LLM pipeline, we constructed a synthetic dataset of 11,997 UML diagrams spanning six major diagram families. Rendering analysis showed that 89.5% of the generated diagrams compile correctly, while invalid cases were detected automatically. To assess quality, we employed a multimodal scoring method that combines Qwen2.5-VL-3B, LLaMA-3.2-11B-Vision-Instruct and Aya-Vision-8B, with weights based on MMMU performance. A study with 94 experts revealed strong alignment between automatic and manual evaluations, yielding a Pearson correlation of r=0.82 and a Fleiss’ Kappa of 0.78. This indicates a high degree of concordance between automated metrics and human judgment. Overall, the results demonstrated that our scoring system is effective and that the proposed generation pipeline produces UML diagrams that are both syntactically correct and semantically coherent. More broadly, the system provides a scalable and reproducible foundation for future work in AI-driven software modeling and multimodal verification.

---

Keywords

---