Scopus

A Comparative Study of Object and Sequence Diagrams in Automated UML Understanding

Năm XB 2026 Tạp chí / Hội thảo Computational Intelligence in Engineering Science: Second International Conference, ICCIES 2026 Vol 3, 390 Đơn vị CNTT DOI / Link https://doi.org/10.1007/978-3-032-21631-1_28 ↗

Tác giả

Van-Viet Nguyen ; Huu-Khanh Nguyen ; Kim-Son Nguyen ; Minh-Hue Luong Thi ; Anh-Tu Bui ✉ ; Duc-Quang Vu ; The-Vinh Nguyen ; Quy-Anh Bui

Tóm tắt

Unified Modeling Language (UML) diagrams are fundamental to software analysis and design, yet their manual creation consti-tutes a significant bottleneck, being labor-intensive and prone to incon-sistencies. While Large Language Models (LLMs) have shown promise in automating this process, a critical gap remains in the comparative analysis of generating different diagram types and in the scalable validation of their semantic correctness. This paper introduces a novel, endto-end pipeline that automates the generation and multimodal evaluation of UML Object and Sequence diagrams. Our workflow first employs a lightweight LLM to synthesize realistic software feature descriptions. Subsequently, a powerful reasoning-centric model, DeepSeek-R1-Distill-Qwen-32B, translates these descriptions into PlantUML code. The core contribution lies in our multimodal evaluation framework, which utilizes an ensemble of three distinct Vision-Language Models (VLMs) Qwen2. 5-VL, LLaMA-3.2-11B-Vision, and Aya-Vision to assess diagrammatic fidelity. Experimental results reveal distinct generation profiles: Object diagrams exhibit a high-competency, low-variability pattern, whereas Sequence diagrams present a polarized outcome, indicating greater modeling complexity. Crucially, our VLM based evaluation scores demonstrate a strong, statistically significant correlation with judgments from 155 human experts, validating VLMs as a reliable and scalable proxy for manual inspection. This work not only establishes the feasibility of a fully automated UML generation and validation workflow but also provides critical insights into the differing complexities of …

Tài liệu tham khảo

[1] Fowler, M.: UML Distilled: A Brief Guide to the Standard Object Modeling Language, 3rd edn. Addison-Wesley Professional, USA (2004)

[2] Jahan, M., et al.: Automated derivation of UML sequence diagrams from user stories: unleashing the power of generative AI vs. a rule-based approach. In: Proceedings of the ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems, pp. 138–148 (2024). https://doi.org/10.1145/3640310.3674081

[3] Deeptimahanti, D.K., Babar, M.A.: An automated tool for generating UML models from natural language requirements. In: 2009 IEEE/ACM International Conference on Automated Software Engineering, pp. 680–682 (2009). https://doi.org/10.1109/ASE.2009.48

[4] Nguyen, V.-V., Nguyen, H.-K., Nguyen, K.-S., Luong Thi Minh, H., Nguyen, T.-V., Vu, D.-Q.: A novel pipeline for automatic UML sequence diagram synthesis and multimodal scoring. In: Thai-Nghe, N., Do, TN., Benferhat, S. (eds.) ISDS 2025. CCIS, vol. 2713, pp. 473–485. Springer, Singapore (2025). https://doi.org/10.1007/978-981-95-3355-8_34

[5] Nguyen, V.-V., Nguyen, H.-K., Nguyen, K.-S., Luong Thi, M.-H., Nguyen, T.-V., Vu, D.-Q.: Automated UML generation: a framework for class diagram synthesis and multimodal validation. In: Dang, T.K., Küng, J., Chung, T.M. (eds.) FDSE 2025. CCIS, vol. 2709, pp. 212–224. Springer, Singapore (2025). https://doi.org/10.1007/978-981-95-4724-1_15

[6] Nguyen Van, V., et al.: Revolutionizing education: an extensive analysis of large language models integration, 4(4), 10–21 (2024). https://irjstem.com/wp-content/uploads/2025/02/IRJSTEM-V4N4-2024-Paper02.pdf

[7] Viet, N.V., Vinh, N.T.: Large language models in software engineering: a systematic review and vision. J. Educ. Sustain. Innov. 2(2), 146–156 (2024). https://doi.org/10.56916/jesi.v2i2.968

[8] Ferrari, A., Abualhaija, S., Arora, C.: Model generation with LLMs: from requirements to UML sequence diagrams. In: 2024 IEEE 32nd International Requirements Engineering Conference Workshops (REW), pp. 291–300. IEEE (2024). https://doi.org/10.1109/REW61692.2024.00044

[9] Pando, B., Castillo, J.: Plantumlgen: a tool for teaching model driven development. In: 2022 17th Iberian Conference on Information Systems and Technologies (CISTI), pp. 1–6. IEEE (2022). https://doi.org/10.23919/CISTI54924.2022.9820348

[10] Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625–5644 (2024). https://doi.org/10.1109/TPAMI.2024.3369699

[11] Robles, K., Fraga, A., Morato, J., Llorens, J.: Towards an ontology-based retrieval of UML class diagrams. Inf. Softw. Technol. 54(1), 72–86 (2012). https://doi.org/10.1016/j.infsof.2011.07.003

[12] Abdouli, M., Karaa, W.B.A., Ghezala, H.B.: Survey of works that transform requirements into UML diagrams. In: 2016 IEEE 14th International Conference on Software Engineering Research, Management and Applications (SERA), pp. 117–123. IEEE (2016)

[13] Van-Viet, N., Nguyen, H.K., Kim-Son, N., Luong, T.M.H., Vu, D.Q., Phung, T.N.: A novel unified framework for automated generation and multimodal validation of UML diagrams. Comput. Model. Eng. Sci. (2026). https://doi.org/10.32604/cmes.2025.075442

[14] Fathiyah, H., Widyani, Y.: Use case generator based on user stories. In: 2024 IEEE International Conference on Data and Software Engineering (ICoDSE), pp. 229–234. IEEE (2024)

[15] Alashqar, A.M.: Automatic generation of UML diagrams from scenario-based user requirements. Jordanian J. Comput. Inf. Technol. 7(2) (2021)

[16] Miller, D., Ortiz, S.: Structured diagram generation with plantuml templates. In: 2021 IEEE Conference on Automated Software Engineering, pp. 214–223 (2021)

[17] Nguyen, T., Roberts, J.: Standardized uml rendering pipelines based on plantUML: a benchmark study. Softw. Syst. Model. 22(3), 901–920 (2023)

[18] Li, X., He, R.: Vision-language understanding of structured diagrams: a comprehensive review. Pattern Recogn. 142, 109–132 (2023)

[19] Brown, M., Fischer, L.: A comparative study of structural and behavioral UML diagram generation. In: International Conference on Software Modeling, pp. 132–144 (2022)

[20] DeepSeek-AI: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)

[21] Touvron, T., et al.: Llama 3: open foundation and instruction-tuned large language models. arXiv preprint arXiv:2309.11510 (2023)

[22] Wang, P., et al.: Qwen2-VL: enhancing vision-language model’s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)

[23] Üstün, A., et al.: Aya model: an instruction finetuned open-access multilingual language model. arXiv preprint arXiv:2402.07827 (2024)

[24] Yue, X., et al.: Mmmu: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556–9567 (2024)

Ghi chú

Van-Viet Nguyen, Huu-Khanh Nguyen, Kim-Son Nguyen, Minh-Hue Luong Thi, Anh-Tu Bui, Duc-Quang Vu, The-Vinh Nguyen, Quy-Anh Bui
← Quay lại danh sách bài báo