{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:58:19Z","timestamp":1769504299321,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3716553.3750787","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:16Z","timestamp":1760188396000},"page":"475-484","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2088-9330","authenticated-orcid":false,"given":"Dongyang","family":"Guo","sequence":"first","affiliation":[{"name":"Human-Centered Technologies for Learning, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8895-4997","authenticated-orcid":false,"given":"Yasmeen","family":"Abdrabou","sequence":"additional","affiliation":[{"name":"Human-Centered Technologies for Learning, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5111-3776","authenticated-orcid":false,"given":"Enkeleda","family":"Thaqi","sequence":"additional","affiliation":[{"name":"Human-Centered Technologies for Learning, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3146-4484","authenticated-orcid":false,"given":"Enkelejda","family":"Kasneci","sequence":"additional","affiliation":[{"name":"Human-Centered Technologies for Learning, Technical University of Munich, Munich, Germany"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"crossref","unstructured":"\u015eeniz\u00a0Harputlu Aksu Erman \u00c7ak\u0131t and Metin Da\u011fdeviren. 2024. Mental workload assessment using machine learning techniques based on eeg and eye tracking data. Applied Sciences 14 6 (2024) 2282.","DOI":"10.3390\/app14062282"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"crossref","unstructured":"Tobias Appel Peter Gerjets Stefan Hoffmann Korbinian Moeller Manuel Ninaus Christian Scharinger Natalia Sevcenko Franz Wortha and Enkelejda Kasneci. 2021. Cross-task and cross-participant classification of cognitive load in an emergency simulation game. IEEE Transactions on Affective Computing 14 2 (2021) 1558\u20131571.","DOI":"10.1109\/TAFFC.2021.3098237"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353735"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"crossref","unstructured":"Gilbert Badaro Mohammed Saeed and Paolo Papotti. 2023. Transformers for tabular data representation: A survey of models and applications. Transactions of the Association for Computational Linguistics 11 (2023) 227\u2013249.","DOI":"10.1162\/tacl_a_00544"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979313"},{"key":"e_1_3_3_3_7_2","first-page":"8182","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Melech\u00a0Stan Gabriela Ben","year":"2024","unstructured":"Gabriela Ben Melech\u00a0Stan, Estelle Aflalo, Raanan\u00a0Yehezkel Rohekar, Anahita Bhiwandiwalla, Shao-Yen Tseng, Matthew\u00a0Lyle Olson, Yaniv Gurwicz, Chenfei Wu, Nan Duan, and Vasudev Lal. 2024. LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8182\u20138187."},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Babette B\u00fchler Efe Bozkir Hannah Deininger Peter Gerjets Ulrich Trautwein and Enkelejda Kasneci. 2024. On task and in sync: Examining the relationship between gaze synchrony and self-reported attention during video lecture learning. Proceedings of the ACM on Human-Computer Interaction 8 ETRA (2024) 1\u201318.","DOI":"10.1145\/3655604"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Simona Caldani Christophe-Lo\u00efc Gerard Hugo Peyre and Maria\u00a0Pia Bucci. 2020. Visual attentional training improves reading capabilities in children with dyslexia: An eye tracker study during a reading task. Brain sciences 10 8 (2020) 558.","DOI":"10.3390\/brainsci10080558"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3204493.3204550"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et\u00a0al. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology 15 3 (2024) 1\u201345.","DOI":"10.1145\/3641289"},{"key":"e_1_3_3_3_13_2","unstructured":"Yuxing Chen Weijie Wang Sylvain Lobry and Camille Kurtz. 2024. An llm agent for automatic geospatial data analysis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.18792 (2024)."},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Jacob Cohen. 1960. A cofficient of agreement for nominal scales. Educational and psychological measurement 20 1 (1960) 37\u201346.","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.97"},{"key":"e_1_3_3_3_16_2","unstructured":"X Fang W Xu FA Tan J Zhang Z Hu Y Qi S Nickleach D Socolinsky S Sengamedu and C Faloutsos. 2024. Large Language Models (LLMs) on Tabular Data: Prediction Generation and Understanding\u2014A Survey. arXiv 2024. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17944 (2024)."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI210059"},{"key":"e_1_3_3_3_18_2","first-page":"10764","volume-title":"International Conference on Machine Learning","author":"Gao Luyu","year":"2023","unstructured":"Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Pal: Program-aided language models. In International Conference on Machine Learning. PMLR, 10764\u201310799."},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Lisa\u00a0A Giacumo and Jeroen Bremen. 2016. Emerging evidence on the use of big data and analytics in workplace learning: A systematic literature review. Quarterly Review of Distance Education 17 4 (2016) 21.","DOI":"10.1108\/QRDE-04-2017-0003"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Xusen Guo Qiming Zhang Junyue Jiang Mingxing Peng Meixin Zhu and Hao\u00a0Frank Yang. 2024. Towards explainable traffic flow prediction with large language models. Communications in Transportation Research 4 (2024) 100150.","DOI":"10.1016\/j.commtr.2024.100150"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Coen Hacking Hilde Verbeek Jan\u00a0PH Hamers and Sil Aarts. 2023. Comparing text mining and manual coding methods: Analysing interview data on quality of care in long-term care for older adults. Plos one 18 11 (2023) e0292578.","DOI":"10.1371\/journal.pone.0292578"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSEE63195.2024.00012"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623175"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Roy\u00a0S Hessels and Ignace\u00a0TC Hooge. 2019. Eye tracking in developmental cognitive neuroscience\u2013The good the bad and the ugly. Developmental cognitive neuroscience 40 (2019) 100710.","DOI":"10.1016\/j.dcn.2019.100710"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Hanyao Huang Ou Zheng Dongdong Wang Jiayi Yin Zijin Wang Shengxuan Ding Heng Yin Chuan Xu Renjie Yang Qian Zheng et\u00a0al. 2023. ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model. International Journal of Oral Science 15 1 (2023) 29.","DOI":"10.1038\/s41368-023-00239-y"},{"key":"e_1_3_3_3_26_2","unstructured":"Jiaxin Huang Shixiang\u00a0Shane Gu Le Hou Yuexin Wu Xuezhi Wang Hongkun Yu and Jiawei Han. 2022. Large language models can self-improve. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.11610 (2022)."},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649902.3653942"},{"key":"e_1_3_3_3_28_2","unstructured":"Enkelejda Kasneci Hong Gao Suleyman Ozdel Virmarie Maquiling Enkeleda Thaqi Carrie Lau Yao Rong Gjergji Kasneci and Efe Bozkir. 2024. Introduction to Eye Tracking: A Hands-On Tutorial for Students and Practitioners. arxiv:https:\/\/arXiv.org\/abs\/2404.15435\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2404.15435"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09903-3_20"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Enkelejda Kasneci Gjergji Kasneci Ulrich Trautwein Tobias Appel Maike Tibus Susanne\u00a0M Jaeggi and Peter Gerjets. 2022. Do your eye movements reveal your performance on an IQ test? A study linking eye movements and socio-demographic information to fluid intelligence. Plos one 17 3 (2022) e0264316.","DOI":"10.1371\/journal.pone.0264316"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Enkelejda Kasneci Kathrin Sessler Stefan K\u00fcchemann Maria Bannert Daryna Dementieva Frank Fischer Urs Gasser Georg Groh Stephan G\u00fcnnemann Eyke H\u00fcllermeier Stephan Krusche Gitta Kutyniok Tilman Michaeli Claudia Nerdel J\u00fcrgen Pfeffer Oleksandra Poquet Michael Sailer Albrecht Schmidt Tina Seidel Matthias Stadler Jochen Weller Jochen Kuhn and Gjergji Kasneci. 2023. ChatGPT for good? On opportunities and challenges of large language models for education. Learning and Individual Differences 103 (2023) 102274. 10.1016\/j.lindif.2023.102274","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Fengfeng Ke Ruohan Liu Zlatko Sokolikj Ibrahim Dahlstrom-Hakki and Maya Israel. 2024. Using eye-tracking in education: review of empirical research and technology. Educational technology research and development 72 3 (2024) 1383\u20131418.","DOI":"10.1007\/s11423-024-10342-4"},{"key":"e_1_3_3_3_33_2","unstructured":"Dong-Ho Lee Jay Pujara Mohit Sewak Ryen\u00a0W White and Sujay\u00a0Kumar Jauhar. 2023. Making large language models better data creators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.20111 (2023)."},{"key":"e_1_3_3_3_34_2","unstructured":"Chen Li Weiqi Wang Jingcheng Hu Yixuan Wei Nanning Zheng Han Hu Zheng Zhang and Houwen Peng. 2024. Common 7b language models already possess strong math capabilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.04706 (2024)."},{"key":"e_1_3_3_3_35_2","unstructured":"Ben Mann N Ryder M Subbiah J Kaplan P Dhariwal A Neelakantan P Shyam G Sastry A Askell S Agarwal et\u00a0al. 2020. Language models are few-shot learners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.14165 1 (2020) 3."},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"crossref","unstructured":"Tom\u00a0M Mitchell. 1999. Machine learning and data mining. Commun. ACM 42 11 (1999) 30\u201336.","DOI":"10.1145\/319382.319388"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"crossref","unstructured":"Waddah Saeed and Christian Omlin. 2023. Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities. Knowledge-based systems 263 (2023) 110273.","DOI":"10.1016\/j.knosys.2023.110273"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Mar\u00eda\u00a0Consuelo S\u00e1iz\u00a0Manzanares Juan\u00a0Jos\u00e9 Rodr\u00edguez\u00a0Diez Ra\u00fal Marticorena\u00a0S\u00e1nchez Maria\u00a0Jose Zaparain\u00a0Yanez and Rebeca Cerezo\u00a0Men\u00e9ndez. 2020. Lifelong learning from sustainable education: An analysis with eye tracking and data mining techniques. Sustainability 12 5 (2020) 1970.","DOI":"10.3390\/su12051970"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Currier Sarah Barton Jane O\u2019Beirne R\u00f3n\u00e1n and Ryan Ben. 2004. Quality assurance for digital learning object repositories: issues for the metadata creation process. ALT-J 12 1 (2004) 5\u201320.","DOI":"10.1080\/0968776042000211494"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Chandan Singh Armin Askari Rich Caruana and Jianfeng Gao. 2023. Augmenting interpretable models with large language models during training. Nature Communications 14 1 (2023) 7913.","DOI":"10.1038\/s41467-023-43713-1"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Vasileios Skaramagkas Giorgos Giannakakis Emmanouil Ktistakis Dimitris Manousos Ioannis Karatzanis Nikolaos\u00a0S Tachos Evanthia Tripoliti Kostas Marias Dimitrios\u00a0I Fotiadis and Manolis Tsiknakis. 2021. Review of eye tracking metrics involved in emotional and cognitive processes. IEEE Reviews in Biomedical Engineering 16 (2021) 260\u2013277.","DOI":"10.1109\/RBME.2021.3066072"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Hedda\u00a0Martina \u0160ola Fayyaz\u00a0Hussain Qureshi and Sarwar Khawaja. 2024. AI Eye-Tracking Technology: A New Era in Managing Cognitive Loads for Online Learners. Education Sciences 14 9 (2024) 933.","DOI":"10.3390\/educsci14090933"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40728-4_56"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"crossref","unstructured":"Jiahui Wang Pavlo Antonenko and Kara Dawson. 2020. Does visual attention to the instructor in online video affect learning and learner perceptions? An eye-tracking analysis. Computers & Education 146 (2020) 103779.","DOI":"10.1016\/j.compedu.2019.103779"},{"key":"e_1_3_3_3_45_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 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_3_46_2","unstructured":"Qingsong Wen Tian Zhou Chaoli Zhang Weiqi Chen Ziqing Ma Junchi Yan and Liang Sun. 2022. Transformers in time series: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2202.07125 (2022)."},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"crossref","unstructured":"Adam Wright Justine Pang Joshua\u00a0C Feblowitz Francine\u00a0L Maloney Allison\u00a0R Wilcox Harley\u00a0Z Ramelson Louise\u00a0I Schneider and David\u00a0W Bates. 2011. A method and knowledge base for automated inference of patient problems from structured data in an electronic medical record. Journal of the American Medical Informatics Association 18 6 (2011) 859\u2013867.","DOI":"10.1136\/amiajnl-2011-000121"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"crossref","unstructured":"Kailai Yang Shaoxiong Ji Tianlin Zhang Qianqian Xie Ziyan Kuang and Sophia Ananiadou. 2023. Towards interpretable mental health analysis with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.03347 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.370"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Yifan Yao Jinhao Duan Kaidi Xu Yuanfang Cai Zhibo Sun and Yue Zhang. 2024. A survey on large language model (llm) security and privacy: The good the bad and the ugly. High-Confidence Computing (2024) 100211.","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695061"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"crossref","unstructured":"Haiyan Zhao Hanjie Chen Fan Yang Ninghao Liu Huiqi Deng Hengyi Cai Shuaiqiang Wang Dawei Yin and Mengnan Du. 2024. Explainability for large language models: A survey. ACM Transactions on Intelligent Systems and Technology 15 2 (2024) 1\u201338.","DOI":"10.1145\/3639372"}],"event":{"name":"ICMI '25: International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:25:43Z","timestamp":1769466343000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716553.3750787"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":50,"alternative-id":["10.1145\/3716553.3750787","10.1145\/3716553"],"URL":"https:\/\/doi.org\/10.1145\/3716553.3750787","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}