{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T10:35:25Z","timestamp":1777113325291,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2027,4,26]],"date-time":"2027-04-26T00:00:00Z","timestamp":1808697600000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["DRL-2112635"],"award-info":[{"award-number":["DRL-2112635"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005246","name":"Institute of Education Sciences","doi-asserted-by":"publisher","award":["R305C240010"],"award-info":[{"award-number":["R305C240010"]}],"id":[{"id":"10.13039\/100005246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3785022.3785109","type":"proceedings-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T09:39:01Z","timestamp":1777109941000},"page":"536-546","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Approach to Evaluating the Effectiveness of Large Language Models for Multimodal Analysis of Embodied Learning in Classrooms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9862-8960","authenticated-orcid":false,"given":"Joyce","family":"Horn Fonteles","sequence":"first","affiliation":[{"name":"Vanderbilt University, Nashville, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8469-0355","authenticated-orcid":false,"given":"Nithin","family":"Sivakumaran","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0856-9587","authenticated-orcid":false,"given":"Clayton","family":"Cohn","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1774-6442","authenticated-orcid":false,"given":"Austin","family":"Coursey","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1670-0054","authenticated-orcid":false,"given":"Shoubin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6689-505X","authenticated-orcid":false,"given":"Elias","family":"Stengel-Eskin","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1690-1626","authenticated-orcid":false,"given":"Ashwin","family":"T. S.","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2965-5354","authenticated-orcid":false,"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2752-3878","authenticated-orcid":false,"given":"Gautam","family":"Biswas","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFSP59764.2023.10372944"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Roger Azevedo and Jennifer\u00a0G Cromley. 2004. Does training on self-regulated learning facilitate students\u2019 learning with hypermedia? Journal of educational psychology 96 3 (2004) 523.","DOI":"10.1037\/0022-0663.96.3.523"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Roger Azevedo and Dragan Ga\u0161evi\u0107. 2019. Analyzing multimodal multichannel data about self-regulated learning with advanced learning technologies: Issues and challenges. 207\u2013210\u00a0pages.","DOI":"10.1016\/j.chb.2019.03.025"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Ge Bai Jie Liu Xingyuan Bu Yancheng He Jiaheng Liu Zhanhui Zhou Zhuoran Lin Wenbo Su Tiezheng Ge Bo Zheng et\u00a0al. 2024. Mt-bench-101: A fine-grained benchmark for evaluating large language models in multi-turn dialogues. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.14762 (2024).","DOI":"10.18653\/v1\/2024.acl-long.401"},{"key":"e_1_3_3_2_6_2","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et\u00a0al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.13923 (2025)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Max Bain Jaesung Huh Tengda Han and Andrew Zisserman. 2023. WhisperX: Time-Accurate Speech Transcription of Long-Form Audio. INTERSPEECH 2023 (2023).","DOI":"10.21437\/Interspeech.2023-78"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Shariq\u00a0Farooq Bhat Reiner Birkl Diana Wofk Peter Wonka and Matthias M\u00fcller. 2023. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth. 10.48550\/ARXIV.2302.12288","DOI":"10.48550\/ARXIV.2302.12288"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2460296.2460316"},{"key":"e_1_3_3_2_10_2","first-page":"6562","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Chen Dongping","year":"2024","unstructured":"Dongping Chen, Ruoxi Chen, Shilin Zhang, Yaochen Wang, Yinuo Liu, Huichi Zhou, Qihui Zhang, Yao Wan, Pan Zhou, and Lichao Sun. 2024. MLLM-as-a-Judge: assessing multimodal LLM-as-a-Judge with vision-language benchmark. In Proceedings of the 41st International Conference on Machine Learning. 6562\u20136595."},{"key":"e_1_3_3_2_11_2","unstructured":"Justin Chih-Yao Chen Archiki Prasad Swarnadeep Saha Elias Stengel-Eskin and Mohit Bansal. 2024. MAgICoRe: Multi-Agent Iterative Coarse-to-Fine Refinement for Reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.12147 (2024)."},{"key":"e_1_3_3_2_12_2","volume-title":"Forty-first International Conference on Machine Learning","author":"Chiang Wei-Lin","year":"2024","unstructured":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios\u00a0Nikolas Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael Jordan, Joseph\u00a0E Gonzalez, et\u00a0al. 2024. Chatbot arena: An open platform for evaluating llms by human preference. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Keith Cochran Clayton Cohn Jean\u00a0Francois Rouet and Peter Hastings. 2025. Comparing Text Augmentation by GPT-3.5 and Llama3 for Evaluating Student Responses. International Journal of Artificial Intelligence in Education (April 2025). 10.1007\/s40593-025-00473-x","DOI":"10.1007\/s40593-025-00473-x"},{"key":"e_1_3_3_2_14_2","unstructured":"Clayton Cohn Nicole Hutchins Gautam Biswas et\u00a0al. 2025. CoTAL: Human-in-the-Loop Prompt Engineering Chain-of-Thought Reasoning and Active Learning for Generalizable Formative Assessment Scoring. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.02323 (2025)."},{"key":"e_1_3_3_2_15_2","first-page":"23182","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Cohn Clayton","year":"2024","unstructured":"Clayton Cohn, Nicole Hutchins, Tuan Le, and Gautam Biswas. 2024. A chain-of-thought prompting approach with llms for evaluating students\u2019 formative assessment responses in science. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a038(21). 23182\u201323190."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Joshua\u00a0A Danish Gabriella Anton Nitasha Mathayas Tessaly Jen Morgan Vickery Sarah Lee Xintian Tu Lana Cosic Mengxi Zhou Efrat Ayalon et\u00a0al. 2022. Designing for shifting learning activities. Journal of Applied Instructional Design (2022).","DOI":"10.59668\/423.8580"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Joshua\u00a0A Danish Noel Enyedy Asmalina Saleh and Megan Humburg. 2020. Learning in embodied activity framework: A sociocultural framework for embodied cognition. International Journal of Computer-Supported Collaborative Learning 15 (2020) 49\u201387.","DOI":"10.1007\/s11412-020-09317-3"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386382"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Lizhou Fan Lingyao Li Zihui Ma Sanggyu Lee Huizi Yu and Libby Hemphill. 2024. A bibliometric review of large language models research from 2017 to 2023. ACM Transactions on Intelligent Systems and Technology 15 5 (2024) 1\u201325.","DOI":"10.1145\/3664930"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-64299-9_1"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Joyce Fonteles Namrata Srivastava Eduardo Davalos Ashwin\u00a0T S and Gautam Biswas. 2024. Designing an AI-Enhanced Timeline for Monitoring Multimodal Interactions in Embodied Learning Environments. International Conference on Computers in Education (Nov. 2024). 10.58459\/icce.2024.4907","DOI":"10.58459\/icce.2024.4907"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Joyce\u00a0Horn Fonteles Clayton Cohn Efrat Ayalon Mengxi Zhou Ashwin TS Eduardo Davalos Zhijian Li Surya Rayala Divya Mereddy Austin Coursey Shruti Jain Yike Zhang Noel Enyedy Joshua Danish and Gautam Biswas. 2025. Analyzing embodied learning in classroom settings: A human-in-the-loop AI approach for multimodal learning analytics. Learning and Instruction (2025). In press.","DOI":"10.1016\/j.learninstruc.2025.102274"},{"key":"e_1_3_3_2_23_2","volume-title":"EDM 2025 \u2013 MMLA Workshop","author":"Fonteles Joyce\u00a0Horn","year":"2025","unstructured":"Joyce\u00a0Horn Fonteles, Clayton Cohn, Divya Mereddy, Ashwin T.\u00a0S., and Gautam Biswas. 2025. Exploring Agentic Multimodal Late Fusion With LLMs for Embodied Learning. In EDM 2025 \u2013 MMLA Workshop (Palermo, Italy). https:\/\/www.researchgate.net\/publication\/394486440_Exploring_Agentic_Multimodal_Late_Fusion_With_LLMs_for_Embodied_Learning"},{"key":"e_1_3_3_2_24_2","unstructured":"Chaoyou Fu Yi-Fan Zhang Shukang Yin Bo Li Xinyu Fang Sirui Zhao Haodong Duan Xing Sun Ziwei Liu Liang Wang et\u00a0al. 2024. Mme-survey: A comprehensive survey on evaluation of multimodal llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15296 (2024)."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Michail Giannakos and Mutlu Cukurova. 2023. The role of learning theory in multimodal learning analytics. British Journal of Educational Technology 54 5 (2023) 1246\u20131267.","DOI":"10.1111\/bjet.13320"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315697048-6"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Jaana Isoh\u00e4t\u00e4l\u00e4 Hanna J\u00e4rvenoja and Sanna J\u00e4rvel\u00e4. 2017. Socially shared regulation of learning and participation in social interaction in collaborative learning. International Journal of Educational Research 81 (2017) 11\u201324.","DOI":"10.1016\/j.ijer.2016.10.006"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Sanna J\u00e4rvel\u00e4 Andy Nguyen Eija Vuorenmaa Jonna Malmberg and Hanna J\u00e4rvenoja. 2023. Predicting regulatory activities for socially shared regulation to optimize collaborative learning. Computers in Human Behavior 144 (2023) 107737.","DOI":"10.1016\/j.chb.2023.107737"},{"key":"e_1_3_3_2_29_2","unstructured":"Dawei Li Bohan Jiang Liangjie Huang Alimohammad Beigi Chengshuai Zhao Zhen Tan Amrita Bhattacharjee Yuxuan Jiang Canyu Chen Tianhao Wu et\u00a0al. 2024. From generation to judgment: Opportunities and challenges of llm-as-a-judge. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.16594 (2024)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Robb Lindgren and David DeLiema. 2022. Viewpoint embodiment and roles in STEM learning technologies. Educational technology research and development 70 3 (2022) 1009\u20131034.","DOI":"10.1007\/s11423-022-10101-3"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Robb Lindgren and Mina Johnson-Glenberg. 2013. Emboldened by embodiment: Six precepts for research on embodied learning and mixed reality. Educational researcher 42 8 (2013) 445\u2013452.","DOI":"10.3102\/0013189X13511661"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706468.3706555"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3506860.3506865"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Anabil Munshi Gautam Biswas Ryan Baker Jaclyn Ocumpaugh Stephen Hutt and Luc Paquette. 2022. Analysing adaptive scaffolds that help students develop self\u2010regulated learning behaviours. Journal of Computer Assisted Learning 39 2 (Dec. 2022) 351\u2013368. 10.1111\/jcal.12761","DOI":"10.1111\/jcal.12761"},{"key":"e_1_3_3_2_35_2","unstructured":"Shu Pu Yaochen Wang Dongping Chen Yuhang Chen Guohao Wang Qi Qin Zhongyi Zhang Zhiyuan Zhang Zetong Zhou Shuang Gong et\u00a0al. 2025. Judge Anything: MLLM as a Judge Across Any Modality. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.17489 (2025)."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.462"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3636555.3636912"},{"key":"e_1_3_3_2_38_2","unstructured":"Aman\u00a0Singh Thakur Kartik Choudhary Venkat\u00a0Srinik Ramayapally Sankaran Vaidyanathan and Dieuwke Hupkes. 2024. Judging the judges: Evaluating alignment and vulnerabilities in llms-as-judges. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.12624 (2024)."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/adics58448.2024.10533619"},{"key":"e_1_3_3_2_40_2","volume-title":"Proceedings of the 15th International Conference of the Learning Sciences-ICLS 2021.","author":"Vickery Morgan","year":"2021","unstructured":"Morgan Vickery, Joshua Danish, Xintian Tu, and Mengxi Zhou. 2021. Scientific Modeling Practices Through Perspective Taking in a Mixed Reality Embodied Learning Environment. In Proceedings of the 15th International Conference of the Learning Sciences-ICLS 2021. International Society of the Learning Sciences."},{"key":"e_1_3_3_2_41_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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.06193 (2025).","DOI":"10.1145\/3728963"},{"key":"e_1_3_3_2_42_2","unstructured":"Xuezhi Wang Jason Wei Dale Schuurmans Quoc Le Ed Chi Sharan Narang Aakanksha Chowdhery and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.11171 (2022)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Philip\u00a0H Winne. 2018. Theorizing and researching levels of processing in self-regulated learning. British Journal of Educational Psychology 88 1 (2018) 9\u201320.","DOI":"10.1111\/bjep.12173"},{"key":"e_1_3_3_2_44_2","unstructured":"Tianyi Xiong Xiyao Wang Dong Guo Qinghao Ye Haoqi Fan Quanquan Gu Heng Huang and Chunyuan Li. 2024. Llava-critic: Learning to evaluate multimodal models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.02712 (2024)."},{"key":"e_1_3_3_2_45_2","unstructured":"Jin Xu Zhifang Guo Jinzheng He Hangrui Hu Ting He Shuai Bai Keqin Chen Jialin Wang Yang Fan Kai Dang et\u00a0al. 2025. Qwen2. 5-omni technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20215 (2025)."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3636555.3636856"},{"key":"e_1_3_3_2_47_2","unstructured":"Lixiang Yan Lele Sha Linxuan Zhao Yuheng Li Roberto Martinez-Maldonado Guanliang Chen Xinyu Li Yueqiao Jin and Dragan Ga\u0161evi\u0107. 2024. Practical and ethical challenges of large language models in education: A systematic scoping review. British Journal of Educational Technology (2024)."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173733"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Fan Zhang Valentin Bazarevsky Andrey Vakunov Andrei Tkachenka George Sung Chuo-Ling Chang and Matthias Grundmann. 2020. MediaPipe Hands: On-device Real-time Hand Tracking. 10.48550\/ARXIV.2006.10214","DOI":"10.48550\/ARXIV.2006.10214"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576050.3576076"},{"key":"e_1_3_3_2_51_2","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Kaiyang Zhou Yongxin Yang Andrea Cavallaro and Tao Xiang. 2021. Learning generalisable omni-scale representations for person re-identification. IEEE transactions on pattern analysis and machine intelligence 44 9 (2021) 5056\u20135069.","DOI":"10.1109\/TPAMI.2021.3069237"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.22318\/icls2024.926221"},{"key":"e_1_3_3_2_54_2","volume-title":"International Conference on Learning Representations","author":"Zhu Lianghui","year":"2025","unstructured":"Lianghui Zhu, Xinggang Wang, and Xinlong Wang. 2025. JudgeLM: Fine-tuned Large Language Models are Scalable Judges. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Barry\u00a0J Zimmerman. 2002. Becoming a self-regulated learner: An overview. Theory into practice 41 2 (2002) 64\u201370.","DOI":"10.1207\/s15430421tip4102_2"}],"event":{"name":"LAK 2026: LAK26: 16th International Learning Analytics and Knowledge Conference","location":"Bergen Norway","acronym":"LAK 2026"},"container-title":["Proceedings of the LAK26: 16th International Learning Analytics and Knowledge Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3785022.3785109","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T09:44:32Z","timestamp":1777110272000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3785022.3785109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":54,"alternative-id":["10.1145\/3785022.3785109","10.1145\/3785022"],"URL":"https:\/\/doi.org\/10.1145\/3785022.3785109","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}