{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T09:53:41Z","timestamp":1790934821120,"version":"4.1.0"},"reference-count":42,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B20156"],"award-info":[{"award-number":["U24B20156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["U24B20156"],"award-info":[{"award-number":["U24B20156"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Model-based systems engineering (MBSE) takes Systems Modeling Language (SysML) as the industrial standard modeling language, yet cloud Large Language Model (LLM)-based SysML generation faces limited domain data, model hallucinations, high hardware cost and confidential data leakage risks. This paper builds a 914-sample SysML PlantUML corpus and proposes a fully offline lightweight framework based on Qwen2.5-Coder-7B-Instruct, integrating 4-bit NF4 Quantized Low-Rank Adaptation (QLoRA) fine-tuning, vector-free Jaccard same-diagram reference retrieval and a three-round syntax correction loop. PlantUML executes syntax parsing while Graphviz only renders layouts. Tested on 131 samples covering five structural and behavioral SysML v1 diagram types, the plain-prompt baseline achieves word-set semantic F1 of 52.94%, and the retrieval-enhanced variant lifts the zero-retry syntax pass rate from 92.37% to 99.28%, with F1 slightly dropping to 50.64%. Running fully local without cloud data transmission, this pipeline offers a privacy-safe lightweight solution for SysML PlantUML modeling and does not support SysML-exclusive requirement or parametric diagrams.<\/jats:p>","DOI":"10.3390\/s26165133","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:01:35Z","timestamp":1786640495000},"page":"5133","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An LLM-Based Framework for the Automatic Generation of SysML Models"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3167-9621","authenticated-orcid":false,"given":"Baoran","family":"An","sequence":"first","affiliation":[{"name":"Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7222-1640","authenticated-orcid":false,"given":"Tao","family":"Lei","sequence":"additional","affiliation":[{"name":"Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8566-8063","authenticated-orcid":false,"given":"Guangtai","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"ref_1","unstructured":"INCOSE (Systems Engineering Vision 2020, 2007). Systems Engineering Vision 2020, Version 2.03."},{"key":"ref_2","unstructured":"Object Management Group (OMG Systems Modeling Language (SysML) Specification, 2024). OMG Systems Modeling Language (SysML) Specification, Version 1.7."},{"key":"ref_3","unstructured":"Kobryn, C. (2026, June 10). SysML v2 Review: The Good, the Bad & the Ugly. Technical Report. Available online: https:\/\/sysml.org\/sysml-v2\/reviews\/good-bad-ugly\/."},{"key":"ref_4","unstructured":"Team, P. (2025). PlantUML Language Reference Guide (Version 1.2025.0), OMG. Official Documentation, Stereotype Extension for SysML v1."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1017\/pds.2025.10267","article-title":"Navigating viewpoints in MBSE: Challenges, potential and pathways for stakeholder participation in industry","volume":"5","author":"Koldewey","year":"2025","journal-title":"Proc. Des. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Khandoker, A., Sint, S., Gessl, G., and Zeman, K. (2026). Toward Demystifying the Missing Links in Model-Based Systems Engineering (MBSE). Systems, 14.","DOI":"10.3390\/systems14020158"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/j.aei.2016.07.003","article-title":"Automated transformation of design text ROM diagram into SysML models","volume":"30","author":"Wan","year":"2016","journal-title":"Adv. Eng. Inform."},{"key":"ref_8","unstructured":"Bao, Y., Yang, Z., Yang, Y., Xie, J., Zhou, Y., Yue, T., Huang, Z., and Guo, P. (2020). An Automated Approach to Generate SysML Models from Restricted Natural Language Requirements in Chinese. [Ph.D. Thesis, Nanjing University of Aeronautics and Astronautics]."},{"key":"ref_9","first-page":"52","article-title":"Automatic analysis modeling method based on structural description of domain requirements","volume":"52","author":"Ouyang","year":"2016","journal-title":"Comput. Eng. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Akundi, A., Ontiveros, J., and Luna, S. (2024). Text-to-Model Transformation: Natural Language-Based Model Generation Framework. Systems, 12.","DOI":"10.3390\/systems12090369"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1007\/s10489-026-07230-0","article-title":"Code generation with large language models: A survey from neural program synthesis to autonomous software development","volume":"56","year":"2026","journal-title":"Appl. Intell."},{"key":"ref_12","unstructured":"Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., and Dong, Z. (2023). A Survey of Large Language Models. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Elhady, A., Agirre, E., and Artetxe, M. (2025). Emergent Abilities of Large Language Models under Continued Pre-training for Language Adaptation, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.acl-long.1547"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yang, X., Cui, R., and Xie, X. (2025, January 20\u201322). AI - Driven Automated UML Modeling Framework Design and Practice. Proceedings of the 2025 IEEE 5th International Conference on Software Engineering and Artificial Intelligence (SEAI), Fuzhou, China.","DOI":"10.1109\/SEAI65851.2025.11108780"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bouamra, Y., Yun, B., Poisson, A., and Armetta, F. (2025, January 25\u201327). SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2. Proceedings of the Practical Applications of Agents and Multi-Agent Systems, Lille, France.","DOI":"10.1007\/978-3-032-07638-0_4"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"35828","DOI":"10.1109\/JIOT.2025.3579920","article-title":"IoT Rule Generation With Cross-View Contrastive Learning and Perplexity-Based Ranking","volume":"12","author":"Cimino","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ge, N., Liu, J., Cao, Z., Chen, Z., and Hu, C. (2025). Generating SysML Behavior Models via Large Language Models: An Empirical Study. Proceedings of the 16th International Conference on Internetware, Internetware 2025, Trondheim, Norway, 20\u201322 June 2025, ACM.","DOI":"10.1145\/3755881.3755926"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Debnath, T., Siddiky, M.N.A., Rahman, M.E., Das, P., Guha, A.K., Rahman, M.R., and Kabir, H.M.D. (2025). A Comprehensive Survey of Prompt Engineering Techniques in Large Language Models. TechRxiv.","DOI":"10.36227\/techrxiv.174140719.96375390\/v1"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Huang, K., Wang, F., Huang, Y., and Arora, C. (2025, January 1\u20135). Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap. Proceedings of the 2025 IEEE 33rd International Requirements Engineering Conference Workshops (REW), Valencia, Spain.","DOI":"10.1109\/REW66121.2025.00081"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Anam, R.K. (2025). Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivity. arXiv.","DOI":"10.31219\/osf.io\/ad9y5_v1"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"127511","DOI":"10.1016\/j.molliq.2025.127511","article-title":"Key factors in neural network performance for liquid crystal texture classification","volume":"428","author":"Piwowarczyk","year":"2025","journal-title":"J. Mol. Liq."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2351","DOI":"10.1007\/s10994-023-06495-7","article-title":"Training data influence analysis and estimation: A survey","volume":"113","author":"Zayd","year":"2024","journal-title":"Mach. Learn."},{"key":"ref_23","unstructured":"Al-Onaizan, Y., Bansal, M., and Chen, Y.N. (2024). A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, ACL."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kazlaris, I., Antoniou, E., Diamantaras, K., and Bratsas, C. (2025). From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs. AI, 6.","DOI":"10.20944\/preprints202508.1942.v1"},{"key":"ref_25","unstructured":"Sun, W., Hu, J., Zhou, Y., Du, J., Lan, D., Wang, K., Zhu, T., Qu, X., Zhang, Y., and Mo, X. (2025). Speed Always Wins: A Survey on Efficient Architectures for Large Language Models. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1145\/3728636","article-title":"Efficient Compressing and Tuning Methods for Large Language Models: A Systematic Literature Review","volume":"57","author":"Kim","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_27","unstructured":"Sahoo, P., Singh, A.K., Saha, S., Jain, V., Mondal, S., and Chadha, A. (2025). A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications. arXiv."},{"key":"ref_28","unstructured":"Yuan, J., Zhang, J., Wen, A., and Hu, X. (2025). The Science of Evaluating Foundation ModelsApplications. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"100144","DOI":"10.1016\/j.nlp.2025.100144","article-title":"The fine art of fine-tuning: A structured review of advanced LLM fine-tuning techniques","volume":"11","author":"Pratap","year":"2025","journal-title":"Nat. Lang. Process. J."},{"key":"ref_30","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Mao, Y., Ge, Y., Fan, Y., Xu, W., Mi, Y., Hu, Z., and Gao, Y. (2024). A survey on LoRA of large language models. Front. Comput. Sci., 19.","DOI":"10.1007\/s11704-024-40663-9"},{"key":"ref_32","first-page":"10088","article-title":"QLoRA: Efficient Finetuning of Quantized LLMs","volume":"Volume 36","author":"Oh","year":"2023","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_33","unstructured":"Bitsandbytes-Foundation (2025). 8-bit and Paged Optimizers. arXiv."},{"key":"ref_34","first-page":"227","article-title":"Training-Testing Data Ratio Selection for Accurate Time Series Forecasting: A COVID-19 Case Study","volume":"Volume 3","author":"Arai","year":"2024","journal-title":"Proceedings of the Future Technologies Conference (FTC) 2024"},{"key":"ref_35","unstructured":"Jha, A., Havens, S., Dohmann, J., Trott, A., and Portes, J. (2023). LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Hasan, M.M., Waseem, M., Kemell, K.K., Rasku, J., Ala-Rantala, J., and Abrahamsson, P. (2026). Assessing Small Language Models for Code Generation: An Empirical Study with Benchmarks. arXiv.","DOI":"10.2139\/ssrn.5472927"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Khosravanian, R., and Aadn\u00f8y, B.S. (2022). Chapter One\u2014Introduction to digital twin, automation and real-time centers. Methods for Petroleum Well Optimization, Gulf Professional Publishing.","DOI":"10.1016\/B978-0-323-90231-1.00006-6"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s10462-025-11368-7","article-title":"A survey on deep learning fundamentals","volume":"58","author":"Tian","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhou, C., Li, Q., Li, C., Yu, J., Liu, Y., Wang, G., Zhang, K., Ji, C., Yan, Q., and He, L. (2024). A comprehensive survey on pretrained foundation models: A history from BERT to ChatGPT. International Journal of Machine Learning and Cybernetics, Springer Nature.","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref_40","unstructured":"NVIDIA Corporation (2025). NVIDIA NIM for Large Language Models (LLMs), NVIDIA Corporation."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1109\/TNNLS.2025.3628671","article-title":"Survey on Efficient Large Language Models: Principles, Algorithms, Applications, and Open Issues","volume":"37","author":"Cheng","year":"2026","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"104350","DOI":"10.1016\/j.compind.2025.104350","article-title":"An agent-based approach for the automatic generation of valid SysMLv2 Models in industrial contexts","volume":"172","author":"Llorens","year":"2025","journal-title":"Comput. Ind."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5133\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:03:33Z","timestamp":1786640613000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":42,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165133"],"URL":"https:\/\/doi.org\/10.3390\/s26165133","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]}}}