{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T22:33:00Z","timestamp":1785364380121,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,3]]},"DOI":"10.1145\/3706468.3706480","type":"proceedings-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:04:11Z","timestamp":1740146651000},"page":"803-809","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Providing Automated Feedback on Formative Science Assessments: Uses of Multimodal Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7138-1427","authenticated-orcid":false,"given":"Ha","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0041-3889","authenticated-orcid":false,"given":"Saerok","family":"Park","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,3]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Kate\u00a0T. Anderson Steven\u00a0J. Zuiker Gita Taasoobshirazi and Daniel\u00a0T. Hickey. 2007. Classroom Discourse as a Tool to Enhance Formative Assessment and Practise in Science. International Journal of Science Education 29 14 (Nov. 2007) 1721\u20131744. 10.1080\/09500690701217295Publisher: Routledge.","DOI":"10.1080\/09500690701217295"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Brian\u00a0R Belland Krista\u00a0D Glazewski and Jennifer\u00a0C Richardson. 2011. Problem-based learning and argumentation: Testing a scaffolding framework to support middle school students\u2019 creation of evidence-based arguments. Instructional Science 39 (2011) 667\u2013694.","DOI":"10.1007\/s11251-010-9148-z"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Arne Bewersdorff Christian Hartmann Marie Hornberger Kathrin Se\u00dfler Maria Bannert Enkelejda Kasneci Gjergji Kasneci Xiaoming Zhai and Claudia Nerdel. 2024. Taking the next step with generative artificial intelligence: The transformative role of multimodal large language models in science education. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.00832 (2024).","DOI":"10.1016\/j.lindif.2024.102601"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Paul Black and Dylan Wiliam. 2009. Developing the theory of formative assessment. Educational Assessment Evaluation and Accountability (formerly: Journal of personnel evaluation in education) 21 (2009) 5\u201331. Publisher: Springer.","DOI":"10.1007\/s11092-008-9068-5"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1037\/13620-004"},{"key":"e_1_3_3_1_7_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry and Amanda Askell. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Zheyi Chen Liuchang Xu Hongting Zheng Luyao Chen Amr Tolba Liang Zhao Keping Yu and Hailin Feng. 2024. Evolution and Prospects of Foundation Models: From Large Language Models to Large Multimodal Models. Computers Materials & Continua 80 2 (2024).","DOI":"10.32604\/cmc.2024.052618"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681484"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Meghan\u00a0Rector Federer Ross\u00a0H Nehm John\u00a0E Opfer and Dennis Pearl. 2015. Using a constructed-response instrument to explore the effects of item position and item features on the assessment of students\u2019 written scientific explanations. Research in Science Education 45 (2015) 527\u2013553.","DOI":"10.1007\/s11165-014-9435-9"},{"key":"e_1_3_3_1_11_2","volume-title":"Formative Assessment for 3D Science Learning: Supporting Ambitious and Equitable Instruction","author":"Furtak Erin\u00a0Marie","year":"2023","unstructured":"Erin\u00a0Marie Furtak. 2023. Formative Assessment for 3D Science Learning: Supporting Ambitious and Equitable Instruction. Teachers College Press. Google-Books-ID: vRPNEAAAQBAJ."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Erin\u00a0Marie Furtak Katharina Kiemer Ruhan\u00a0Kizil Circi Rebecca Swanson Vanessa de Le\u00f3n Deb Morrison and Sara\u00a0C. Heredia. 2016. Teachers\u2019 formative assessment abilities and their relationship to student learning: findings from a four-year intervention study. Instructional Science 44 3 (June 2016) 267\u2013291. 10.1007\/s11251-016-9371-3","DOI":"10.1007\/s11251-016-9371-3"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Scott\u00a0E. Grapin and Laura Ascenzi-Moreno. 2024. Expansive assessment of expansive abilities: Teachers\u2019 perspectives and practices with multimodal and translanguaged content assessments. Learning and Instruction 92 (Aug. 2024) 101925. 10.1016\/j.learninstruc.2024.101925","DOI":"10.1016\/j.learninstruc.2024.101925"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Scott\u00a0E Grapin and Lorena Llosa. 2022. Multimodal tasks to assess English learners and their peers in science. Educational assessment 27 1 (2022) 46\u201370. Publisher: Taylor & Francis.","DOI":"10.1080\/10627197.2022.2028139"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642216"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Che-Yu Kuo and Hsin-Kai Wu. 2013. Toward an integrated model for designing assessment systems: An analysis of the current status of computer-based assessments in science. Computers & Education 68 (Oct. 2013) 388\u2013403. 10.1016\/j.compedu.2013.06.002","DOI":"10.1016\/j.compedu.2013.06.002"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"J\u00a0Richard Landis and Gary\u00a0G Koch. 1977. An application of hierarchical kappa-type statistics in the assessment of majority agreement among multiple observers. Biometrics (1977) 363\u2013374.","DOI":"10.2307\/2529786"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Gyeong-Geon Lee Ehsan Latif Xuansheng Wu Ninghao Liu and Xiaoming Zhai. 2024. Applying large language models and chain-of-thought for automatic scoring. Computers and Education: Artificial Intelligence 6 (2024) 100213. Publisher: Elsevier.","DOI":"10.1016\/j.caeai.2024.100213"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Hee-Sun Lee Gey-Hong Gweon Trudi Lord Noah Paessel Amy Pallant and Sarah Pryputniewicz. 2021. Machine Learning-Enabled Automated Feedback: Supporting Students\u2019 Revision of Scientific Arguments Based on Data Drawn from Simulation. Journal of Science Education and Technology 30 2 (April 2021) 168\u2013192. 10.1007\/s10956-020-09889-7","DOI":"10.1007\/s10956-020-09889-7"},{"key":"e_1_3_3_1_22_2","unstructured":"Richard Lehrer and Leona Schauble. 2015. The development of scientific thinking. Handbook of child psychology and developmental science 2 7 (2015) 671\u2013714. Publisher: Wiley Hoboken NJ."},{"key":"e_1_3_3_1_23_2","unstructured":"Haiying Li Janice Gobert and Rachel Dickler. 2017. Automated Assessment for Scientific Explanations in On-Line Science Inquiry. International Educational Data Mining Society (2017). Publisher: ERIC."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Stephanie Link Mohaddeseh Mehrzad and Mohammad Rahimi. 2022. Impact of automated writing evaluation on teacher feedback student revision and writing improvement. Computer Assisted Language Learning 35 4 (2022) 605\u2013634. Publisher: Taylor & Francis.","DOI":"10.1080\/09588221.2020.1743323"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Ou\u00a0Lydia Liu Joseph\u00a0A Rios Michael Heilman Libby Gerard and Marcia\u00a0C Linn. 2016. Validation of automated scoring of science assessments. Journal of Research in Science Teaching 53 2 (2016) 215\u2013233. Publisher: Wiley Online Library.","DOI":"10.1002\/tea.21299"},{"key":"e_1_3_3_1_26_2","unstructured":"Pan Lu Hritik Bansal Tony Xia Jiacheng Liu Chunyuan Li Hannaneh Hajishirzi Hao Cheng Kai-Wei Chang Michel Galley and Jianfeng Gao. 2023. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.02255 (2023)."},{"key":"e_1_3_3_1_27_2","first-page":"387","volume-title":"International conference on data intelligence and cognitive informatics","author":"Marvin Ggaliwango","year":"2023","unstructured":"Ggaliwango Marvin, Nakayiza Hellen, Daudi Jjingo, and Joyce Nakatumba-Nabende. 2023. Prompt engineering in large language models. In International conference on data intelligence and cognitive informatics. Springer, 387\u2013402."},{"key":"e_1_3_3_1_28_2","unstructured":"Katherine\u00a0L McNeill and Joseph\u00a0S Krajcik. 2011. Supporting Grade 5-8 Students in Constructing Explanations in Science: The Claim Evidence and Reasoning Framework for Talk and Writing. Pearson (2011)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Elizabeth\u00a0Birr Moje. 2007. Chapter 1 Developing Socially Just Subject-Matter Instruction: A Review of the Literature on Disciplinary Literacy Teaching. Review of Research in Education 31 1 (March 2007) 1\u201344. 10.3102\/0091732X07300046001Publisher: American Educational Research Association.","DOI":"10.3102\/0091732X07300046001"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Ashlyn\u00a0E. Pierson Douglas\u00a0B. Clark and Corey\u00a0E. Brady. 2021. Scientific modeling and translanguaging: A multilingual and multimodal approach to support science learning and engagement. Science Education 105 4 (2021) 776\u2013813. 10.1002\/sce.21622_eprint: https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/sce.21622.","DOI":"10.1002\/sce.21622"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","unstructured":"Ashlyn\u00a0E. Pierson D.\u00a0Teo Keifert Sarah\u00a0J. Lee Andrea Henrie Heather\u00a0J. Johnson and Noel Enyedy. 2023. Multiple Representations in Elementary Science: Building Shared Understanding while Leveraging Students\u2019 Diverse Ideas and Practices. Journal of Science Teacher Education 34 7 (Oct. 2023) 707\u2013731. 10.1080\/1046560X.2022.2143612Publisher: Routledge _eprint: https:\/\/doi.org\/10.1080\/1046560X.2022.2143612.","DOI":"10.1080\/1046560X.2022.2143612"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Angi Shelton Andrew Smith Eric Wiebe Courtney Behrle Ruth Sirkin and James Lester. 2016. Drawing and writing in digital science notebooks: Sources of formative assessment data. Journal of Science Education and Technology 25 (2016) 474\u2013488. Publisher: Springer.","DOI":"10.1007\/s10956-016-9607-7"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Andy Smith Samuel Leeman-Munk Angi Shelton Bradford Mott Eric Wiebe and James Lester. 2018. A multimodal assessment framework for integrating student writing and drawing in elementary science learning. IEEE Transactions on Learning Technologies 12 1 (2018) 3\u201315. Publisher: IEEE.","DOI":"10.1109\/TLT.2018.2799871"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Yishen Song Liming Guo and Qinhua Zheng. 2024. Measuring scientific inquiry ability related to hands-on practice: An automated approach based on multimodal data analysis. Education and Information Technologies (2024) 1\u201331.","DOI":"10.1007\/s10639-024-12991-7"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Judith Stanja Wolfgang Gritz Johannes Krugel Anett Hoppe and Sarah Dannemann. 2023. Formative assessment strategies for students\u2019 conceptions\u2014The potential of learning analytics. British Journal of Educational Technology 54 1 (2023) 58\u201375. 10.1111\/bjet.13288_eprint: https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/bjet.13288.","DOI":"10.1111\/bjet.13288"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","unstructured":"Kok-Sing Tang. 2023. Distribution of Visual Representations Across Scientific Genres in Secondary Science Textbooks: Analysing Multimodal Genre Pattern of Verbal-Visual Texts. Research in Science Education 53 2 (April 2023) 357\u2013375. 10.1007\/s11165-022-10058-6","DOI":"10.1007\/s11165-022-10058-6"},{"key":"e_1_3_3_1_37_2","first-page":"698","volume-title":"Proceedings of the 17th International Conference on Educational Data Mining","author":"Tian Xiaoyi","year":"2024","unstructured":"Xiaoyi Tian, Amogh Mannekote, Carly\u00a0E Solomon, Yukyeong Song, Christine\u00a0Fry Wise, Tom McKlin, Joanne Barrett, Kristy\u00a0Elizabeth Boyer, and Maya Israel. 2024. Examining LLM Prompting Strategies for Automatic Evaluation of Learner-Created Computational Artifacts. In Proceedings of the 17th International Conference on Educational Data Mining. 698\u2013706."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Claudia von Aufschnaiter and Alicia\u00a0C. Alonzo. 2018. Foundations of formative assessment: Introducing a learning progression to guide preservice physics teachers\u2019 video-based interpretation of student thinking. Applied Measurement in Education 31 2 (April 2018) 113\u2013127. 10.1080\/08957347.2017.1408629Publisher: Routledge _eprint: https:\/\/doi.org\/10.1080\/08957347.2017.1408629.","DOI":"10.1080\/08957347.2017.1408629"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Hanna Wanselin Kristina Danielsson and Susanne Wikman. 2022. Analysing Multimodal Texts in Science\u2014a Social Semiotic Perspective. Research in Science Education 52 3 (June 2022) 891\u2013907. 10.1007\/s11165-021-10027-5","DOI":"10.1007\/s11165-021-10027-5"},{"key":"e_1_3_3_1_40_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Christopher\u00a0D Wilson Kevin\u00a0C Haudek Jonathan\u00a0F Osborne Zo\u00eb\u00a0E Buck\u00a0Bracey Tina Cheuk Brian\u00a0M Donovan Molly\u00a0AM Stuhlsatz Marisol\u00a0M Santiago and Xiaoming Zhai. 2024. Using automated analysis to assess middle school students\u2019 competence with scientific argumentation. Journal of Research in Science Teaching 61 1 (2024) 38\u201369. Publisher: Wiley Online Library.","DOI":"10.1002\/tea.21864"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Rachel\u00a0E Wilson and Leslie\u00a0U Bradbury. 2016. The pedagogical potential of drawing and writing in a primary science multimodal unit. International Journal of Science Education 38 17 (2016) 2621\u20132641. Publisher: Taylor & Francis.","DOI":"10.1080\/09500693.2016.1255369"},{"key":"e_1_3_3_1_43_2","unstructured":"Zhengyuan Yang Linjie Li Kevin Lin Jianfeng Wang Chung-Ching Lin Zicheng Liu and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.17421 9 1 (2023) 1."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Xiaoming Zhai Peng He and Joseph Krajcik. 2022. Applying machine learning to automatically assess scientific models. Journal of Research in Science Teaching 59 10 (2022) 1765\u20131794. Publisher: Wiley Online Library.","DOI":"10.1002\/tea.21773"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","unstructured":"Mengxiao Zhu Ou\u00a0Lydia Liu and Hee-Sun Lee. 2020. The effect of automated feedback on revision behavior and learning gains in formative assessment of scientific argument writing. Computers & Education 143 (Jan. 2020) 103668. 10.1016\/j.compedu.2019.103668","DOI":"10.1016\/j.compedu.2019.103668"},{"key":"e_1_3_3_1_46_2","unstructured":"Zichen Zhu Yang Xu Lu Chen Jingkai Yang Yichuan Ma Yiming Sun Hailin Wen Jiaqi Liu Jinyu Cai and Yingzi Ma. 2024. Multi: Multimodal Understanding Leaderboard with Text and Images. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.03173 (2024)."}],"event":{"name":"LAK '25: The 15th International Learning Analytics and Knowledge Conference","location":"Dublin Ireland","acronym":"LAK 2025"},"container-title":["Proceedings of the 15th International Learning Analytics and Knowledge Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706468.3706480","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706468.3706480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:04Z","timestamp":1750295884000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706468.3706480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,3]]},"references-count":45,"alternative-id":["10.1145\/3706468.3706480","10.1145\/3706468"],"URL":"https:\/\/doi.org\/10.1145\/3706468.3706480","relation":{},"subject":[],"published":{"date-parts":[[2025,3,3]]},"assertion":[{"value":"2025-03-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}