TY  - EJOU
AU  - Nguyen, Van-Viet 
AU  - Nguyen, Huu-Khanh 
AU  - Nguyen, Kim-Son 
AU  - Luong, Thi Minh-Hue 
AU  - Vu, Duc-Quang 
AU  - Phung, Trung-Nghia 
AU  - Nguyen, The-Vinh 

TI  - A Novel Unified Framework for Automated Generation and Multimodal Validation of UML Diagrams
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2026
VL  - 146
IS  - 1
SN  - 1526-1506

AB  - 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 <mml:math id="mml-ieqn-1"><mml:mi>r</mml:mi><mml:mo>=</mml:mo><mml:mn>0.82</mml:mn></mml:math> and a Fleiss’ Kappa of <mml:math id="mml-ieqn-2"><mml:mn>0.78</mml:mn></mml:math>. 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.
KW  - Automated dataset generation; vision-language models; multimodal validation; software engineering automation; UMLCode

DO  - 10.32604/cmes.2025.075442