{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T20:20:12Z","timestamp":1791231612399,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786580.3786985","type":"proceedings-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T14:37:06Z","timestamp":1783953426000},"page":"221-231","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Scaling Assessment of Student Models with LLMs: Integrating Feedback into Practice"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1509-7842","authenticated-orcid":false,"given":"Maximilian","family":"S\u00f6lch","sequence":"first","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4552-644X","authenticated-orcid":false,"given":"Stephan","family":"Krusche","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Luciane T.\u00a0W. Agner Timothy\u00a0C. Lethbridge and Inali\u00a0W. Soares. 2019. Student Experience with Software Modeling Tools. Software & Systems Modeling 18 5 (2019) 3025\u20133047.","DOI":"10.1007\/s10270-018-00709-6"},{"key":"e_1_3_3_2_3_2","first-page":"1","volume-title":"2024 International Joint Conference on Neural Networks (IJCNN)","author":"Ardimento Pasquale","year":"2024","unstructured":"Pasquale Ardimento, Mario\u00a0Luca Bernardi, and Marta Cimitile. 2024. Teaching UML Using a RAG-based LLM. In 2024 International Joint Conference on Neural Networks (IJCNN). 1\u20138."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652620.3687784"},{"key":"e_1_3_3_2_5_2","unstructured":"Sebastian Baltes Florian Angermeir Chetan Arora Marvin\u00a0Mu\u00f1oz Bar\u00f3n Chunyang Chen Lukas B\u00f6hme Fabio Calefato Neil Ernst Davide Falessi Brian Fitzgerald Davide Fucci Marcos Kalinowski Stefano Lambiase Daniel Russo Mircea Lungu Lutz Prechelt Paul Ralph Rijnard van Tonder Christoph Treude and Stefan Wagner. 2025. Guidelines for Empirical Studies in Software Engineering Involving Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2508.15503\u00a0[cs]"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","first-page":"238","DOI":"10.18653\/v1\/2025.acl-short.20","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Bavaresco Anna","year":"2025","unstructured":"Anna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi, Desmond Elliott, Raquel Fern\u00e1ndez, Albert Gatt, Esam Ghaleb, Mario Giulianelli, Michael Hanna, Alexander Koller, Andre Martins, Philipp Mondorf, Vera Neplenbroek, Sandro Pezzelle, Barbara Plank, David Schlangen, Alessandro Suglia, Aditya\u00a0K Surikuchi, Ece Takmaz, and Alberto Testoni. 2025. LLMs Instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad\u00a0Taher Pilehvar (Eds.). Association for Computational Linguistics, 238\u2013255."},{"key":"e_1_3_3_2_7_2","volume-title":"2. Workshop \"Automatische Bewertung von Programmieraufgaben\" (ABP\u20192015)","author":"Beck Philip-Daniel","year":"2015","unstructured":"Philip-Daniel Beck, Thomas Mahlmeister, Marianus Ifland, and Frank Puppe. 2015. COCLAC - Feedback Generation for Combined UML Class and Activity Diagram Modeling Tasks. In 2. Workshop \"Automatische Bewertung von Programmieraufgaben\" (ABP\u20192015)."},{"key":"e_1_3_3_2_8_2","series-title":"(MODELS \u201919 Companion)","first-page":"700","volume-title":"Proceedings of the 22nd International Conference on Model Driven Engineering Languages and Systems Companion","author":"Bian Weiyi","year":"2021","unstructured":"Weiyi Bian, Omar Alam, and J\u00f6rg Kienzle. 2021. Automated Grading of Class Diagrams. In Proceedings of the 22nd International Conference on Model Driven Engineering Languages and Systems Companion(MODELS \u201919 Companion). IEEE Press, 700\u2013709."},{"key":"e_1_3_3_2_9_2","first-page":"158","volume-title":"17th International Conference on Computer Supported Education","author":"Bouali Nacir","year":"2025","unstructured":"Nacir Bouali, Marcus Gerhold, Tosif Rehman, and Faizan Ahmed. 2025. Toward Automated UML Diagram Assessment: Comparing LLM-Generated Scores with Teaching Assistants. In 17th International Conference on Computer Supported Education. 158\u2013169."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Javier C\u00e1mara Javier Troya Lola Burgue\u00f1o and Antonio Vallecillo. 2023. On the Assessment of Generative AI in Modeling Tasks: An Experience Report with ChatGPT and UML. Software and Systems Modeling 22 3 (2023) 781\u2013793.","DOI":"10.1007\/s10270-023-01105-5"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0J. Cowling. 2005. The Role of Modelling in the Software Engineering Curriculum. Journal of Systems and Software 75 1 (2005) 41\u201353.","DOI":"10.1016\/j.jss.2004.02.021"},{"key":"e_1_3_3_2_12_2","series-title":"(MODELS \u201920)","first-page":"1","volume-title":"Proceedings of the 23rd ACM\/IEEE International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings","author":"Farias Kleinner","year":"2020","unstructured":"Kleinner Farias and Bruno\u00a0C. da Silva. 2020. What\u2019s the Grade of Your Diagram? Towards a Streamlined Approach for Grading UML Diagrams. In Proceedings of the 23rd ACM\/IEEE International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings(MODELS \u201920). Association for Computing Machinery, 1\u20132."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Reza Fauzan Daniel Siahaan Siti Rochimah and Evi Triandini. 2021. Automated Class Diagram Assessment Using Semantic and Structural Similarities. International Journal of Intelligent Engineering and Systems 14 2 (2021) 52\u201366.","DOI":"10.22266\/ijies2021.0430.06"},{"key":"e_1_3_3_2_14_2","unstructured":"Sebastian G\u00fcrtl Gloria Schimetta David Kerschbaumer Michael Liut and Alexander Steinmaurer. 2025. Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2507.23470\u00a0[cs]"},{"key":"e_1_3_3_2_15_2","unstructured":"Robert\u00a0W. Hasker. 2011. UMLGrader: An Automated Class Diagram Grader. J. Comput. Sci. Coll. 27 1 (2011) 47\u201354."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"John Hattie and Helen Timperley. 2007. The Power of Feedback. Review of Educational Research 77 1 (2007) 81\u2013112.","DOI":"10.3102\/003465430298487"},{"key":"e_1_3_3_2_17_2","first-page":"S1C\u201321","volume-title":"33rd Annual Frontiers in Education, 2003. FIE 2003.","author":"Henderson P.B.","year":"2003","unstructured":"P.B. Henderson. 2003. The Role of Modeling in Software Engineering Education. In 33rd Annual Frontiers in Education, 2003. FIE 2003. , Vol.\u00a03. S1C\u201321."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Gil Hoggarth and Mike Lockyer. 1998. An Automated Student Diagram Assessment System. SIGCSE Bull. 30 3 (1998) 122\u2013124.","DOI":"10.1145\/290320.283089"},{"key":"e_1_3_3_2_19_2","volume-title":"Hawaii International Conference on System Sciences","author":"Krusche Stephan","year":"2022","unstructured":"Stephan Krusche. 2022. Semi-Automatic Assessment of Modeling Exercises Using Supervised Machine Learning. In Hawaii International Conference on System Sciences. hdl:10125\/79439"},{"key":"e_1_3_3_2_20_2","first-page":"284","volume-title":"Proceedings of the 49th Technical Symposium on Computer Science Education (SIGCSE)","author":"Krusche Stephan","year":"2018","unstructured":"Stephan Krusche and Andreas Seitz. 2018. Artemis: An Automatic Assessment Management System for Interactive Learning. In Proceedings of the 49th Technical Symposium on Computer Science Education (SIGCSE). ACM, 284\u2013289."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377814.3381701"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Pedro\u00a0C. Mendon\u00e7a Filipe Quintal and F\u00e1bio Mendon\u00e7a. 2025. Evaluating LLMs for Automated Scoring in Formative Assessments. Applied Sciences 15 5 (2025) 2787.","DOI":"10.3390\/app15052787"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1109\/ICALT.2019.00061","volume-title":"2019 IEEE 19th International Conference on Advanced Learning Technologies (ICALT)","volume":"2161","author":"Pinheiro\u00a0Cavalcanti Anderson","year":"2019","unstructured":"Anderson Pinheiro\u00a0Cavalcanti, Rafael Ferreira Leite de Mello, Vitor Rolim, M\u00e1verick Andr\u00e9, Fred Freitas, and Dragan Ga\u0161evic. 2019. An Analysis of the Use of Good Feedback Practices in Online Learning Courses. In 2019 IEEE 19th International Conference on Advanced Learning Technologies (ICALT) , Vol.\u00a02161-377X. 153\u2013157."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Per Runeson and Martin H\u00f6st. 2009. Guidelines for Conducting and Reporting Case Study Research in Software Engineering. Empirical Software Engineering 14 2 (2009) 131\u2013164.","DOI":"10.1007\/s10664-008-9102-8"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3727247"},{"key":"e_1_3_3_2_26_2","volume-title":"BNAIC\/BENELEARN","author":"Stikkolorum Dave\u00a0R.","year":"2019","unstructured":"Dave\u00a0R. Stikkolorum, P.\u00a0V.\u00a0D. Putten, Caroline Sperandio, and M. Chaudron. 2019. Towards Automated Grading of UML Class Diagrams with Machine Learning. In BNAIC\/BENELEARN."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2591708.2602657"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Pete Thomas Neil Smith and Kevin Waugh. 2008. Automatically Assessing Graph-based Diagrams. Learning Media and Technology 33 3 (2008) 249\u2013267.","DOI":"10.1080\/17439880802324251"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/978-3-540-69489-2_36","volume-title":"Models in Software Engineering","author":"Vallino James","year":"2007","unstructured":"James Vallino. 2007. If You\u2019re Not Modeling, You\u2019re Just Programming: Modeling Throughout an Undergraduate Software Engineering Program. In Models in Software Engineering, Thomas K\u00fchne (Ed.). Springer, 291\u2013300."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Yen Vo Heather Rickels Catherine Welch and Stephen Dunbar. 2023. Human Scoring versus Automated Scoring for English Learners in a Statewide Evidence-Based Writing Assessment. Assessing Writing 56 (2023) 100719.","DOI":"10.1016\/j.asw.2023.100719"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Chong Wang Beian Wang Peng Liang and Jie Liang. 2026. Assessing UML Diagrams by GPT: Implications for Education. Journal of Systems and Software 234 (2026) 112709.","DOI":"10.1016\/j.jss.2025.112709"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Ruiqi Wang Jiyu Guo Cuiyun Gao Guodong Fan Chun\u00a0Yong Chong and Xin Xia. 2025. Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering. Proc. ACM Softw. Eng. 2 ISSTA (2025) ISSTA086:1955\u2013ISSTA086:1977.","DOI":"10.1145\/3728963"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1007\/978-3-319-19773-9_123","volume-title":"Artificial Intelligence in Education","author":"Weerasinghe Amali","year":"2015","unstructured":"Amali Weerasinghe and Bernard Evans. 2015. UML-IT: An ITS to Teach Multiple Modelling Tasks. In Artificial Intelligence in Education, Cristina Conati, Neil Heffernan, Antonija Mitrovic, and M.\u00a0Felisa Verdejo (Eds.). Springer International Publishing, 816\u2013819."},{"key":"e_1_3_3_2_34_2","unstructured":"Wei Xia Shaoguang Mao and Chanjing Zheng. 2024. Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition\u2014Taking TOEFL Independent Writing Task for Example. arxiv:https:\/\/arXiv.org\/abs\/2401.03401\u00a0[cs]"}],"event":{"name":"ICSE-SEET '26: 2026 IEEE\/ACM 48th International Conference on Software Engineering","location":"Rio de Janeiro Brazil","acronym":"ICSE-SEET '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the IEEE\/ACM 48th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786580.3786985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T14:38:50Z","timestamp":1783953530000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786580.3786985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":33,"alternative-id":["10.1145\/3786580.3786985","10.1145\/3786580"],"URL":"https:\/\/doi.org\/10.1145\/3786580.3786985","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}