LLM nomads: an exploration of why users alternate among different LLMs
DOI:
https://doi.org/10.47989/ir31260433Abstract
Introduction. This study explores behavioural mechanisms behind users’ frequent shifting between different large language models (LLMs), analyses the factors influencing such shifting behaviour and their interaction pathways, and provides both theoretical and practical insights into user decision-making logic in multi-model interaction scenarios.
Method. Based on the Uses and Gratifications Theory, this study constructs a theoretical model, encompassing gratification dimensions, usage dimensions, and behavioural influence dimensions, and employs structural equation modelling to examine the effects of each variable on shifting behaviour.
Analysis. This study collected data from 315 valid respondents via questionnaires and analysed users’ nomadic behaviour across different LLMs.
Results. The depth and professionalism of content generated by LLMs, along with users’ information seeking needs, significantly and positively influence perceived usefulness, which in turn negatively suppresses shifting behaviour. Emotional and interaction experiences reduce user shifting by enhancing perceived ease of use, while user satisfaction indirectly affects shifting behaviour by shaping usage habits.
Conclusions. This study introduces the concept of “LLM Nomads” for the first time, filling a gap in research on user behaviour involving frequent shifting between models. It offers developers a practical pathway to enhance user retention, providing valuable guidance for mitigating homogeneous competition among products.
References
Ahn, J. A. & Seo, S. (2018), “Consumer responses to interactive restaurant self-service technology (IRSST): The role of gadget-loving propensity”, International Journal of Hospitality Management, 74, 109-121. https://doi.org/10.1016/j.ijhm.2018.02.020
Alajmi, M. A. & Ali, M. S. (2023), “International students’ university decision quality: The effect of online environment quality, information-task fit, perceived usefulness and social influence”, Information Development, 39(4), 720-738. https://doi.org/10.1177/02666669211049107
Albertson, D. & Ju, B. (2016), “Perceived self-efficacy and interactive video retrieval”, Journal of Documentation, 72(5), 832-857. https://doi.org/10.1108/JD-09-2015-0109
Amoako-Gyampah, K. (2007), “Perceived usefulness, user involvement and behavioral intention: an empirical study of ERP implementation”, Computers in Human Behavior, 23(3), 1232-1248. https://doi.org/10.1016/j.chb.2004.12.002
Atzil-Slonim, D., Eliassaf, A., Warikoo, N., Paz, A., Haimovitz, S., Mayer, T. & Gurevych, I. (2024), “Leveraging Natural Language Processing to Study Emotional Coherence in Psychotherapy”, Psychotherapy, 61(1), 82-92. https://doi.org/10.1037/pst0000517
Augenstein, I., Baldwin, T., Cha, M., Chakraborty, T., Ciampaglia, G. L. & Corney, D. (2024), “Factuality challenges in the era of large language models and opportunities for fact-checking”, Nature Machine Intelligence, 6(8), 852-863. https://doi.org/10.1038/s42256-024-00881-z
Bak, M. & Chin, J. (2024), “The potential and limitations of large language models in identification of the states of motivations for facilitating health behavior change”, Journal of the American Medical Informatics Association, 31(9), 2047-2053. https://doi.org/10.1093/jamia/ocae057
Bellini, V., Semeraro, F., Montomoli, J., Cascella, M. & Bignami, E. (2024), “Between human and AI: assessing the reliability of AI text detection tools”, Current Medical Research and Opinion, 40(3), 353-358. https://doi.org/10.1080/03007995.2024.2310086
Boonstra, M. J., Weissenbacher, D., Moore, J. H., Gonzalez-Hernandez, G. & Asselbergs, F. W. (2024), “Artificial intelligence: revolutionizing cardiology with large language models”, European Heart Journal, 45(5), 332-345. https://doi.org/10.1093/eurheartj/ehad838
Chan, V. N. (2024), “Using a virtual reality mobile application for interpreting learning: listening to the students’ voice”, Interactive Learning Environments, 32(6), 2438-2451. https://doi.org/10.1080/10494820.2022.2147958
Chen, L. Y., Hsiao, B. & Hwang, W. L. (2022), “Continuance usage of mobile SMS: the moderating role of habit”, International Journal of Mobile Communications, 20(1), 73-104. https://doi.org/10.1504/IJMC.2022.119993
Chen, S. Y., Huang, L., Shadiev, R. & Hu, P. Y. (2025), “An extension of UTAUT model to understand elementary school students’ behavioral intention to use an online homework platform”, Education and Information Technologies, 30(1), 229-255. https://doi.org/10.1007/s10639-024-12852-3
Chin, W. W., Thatcher, J. B. & Wright, R. T. (2012), “Assessing common method bias: problems with the ULMC technique”, MIS Quarterly, 36(3), 1003-1019. https://doi.org/10.2307/41703491
Deng, J. W., Zubair, A., Park, Y. J., Affan, E. & Zuo, Q. K. (2024), “The use of LLMs in medicine: proceeding with caution”, Current Medical Research and Opinion, 40(2), 151-153. https://doi.org/10.1080/03007995.2023.2295411
Gartlehner, G., Kahwati, L., Hilscher, R., Thomas, I., Kugley, S. & Crotty, K. (2024), “Data extraction for evidence synthesis using a large language model: A proof-of-concept study”, Research Synthesis Methods, 15(4), 576-589. https://doi.org/10.1002/jrsm.1710
Guo, C. Q. & Ming, J. R. (2020), “Integrated Model and Empirical Study on Users’ Continuous Usage Willingness of Mobile Library”, Journal of Modern Information, 40(9), 79-89. https://doi.org/10.3969/j.issn.1008-0821.2020.09.009
Hanson, C. L., Magnusson, B. M., Crandall, A. A., Barnes, M. D., McFarland, E. & Smith, M. (2024), “Life experience pathways to college student emotional and mental health: A structural equation model”, Journal of American College Health, 72(3), 826-833. https://doi.org/10.1080/07448481.2022.2058328
Jeon, J. & Lee, S.Y. (2023), “ large language models in education: A focus on the complementary relationship between human teachers and ChatGPT”, Education and Information Technologies, 28(12), 15873-15892. https://doi.org/10.1007/s10639-023-11834-1
Katz, E., Blumler, J. G. & Gurevitch, M. (1973), “Uses and Gratifications Research”, The Public Opinion Quarterly, 37(4), 509-523. https://doi.org/10.1086/268109
Lee, G. H., Lee, K. J., Jeong, B. & Kim, T. (2024), “Developing Personalized Marketing Service Using Generative AI”, IEEE Access, 12, 22394-22402. https://doi.org/10.1109/ACCESS.2024.3361946
Lee, J., Hicke, Y., Yu, R. Z., Brooks, C. & Kizilcec, R. F. (2024), “The life cycle of large language models in education: A framework for understanding sources of bias”, British Journal of Educational Technology, 55(5), 1982-2002. https://doi.org/10.1111/bjet.13505
Lee, S. & Park, G. (2023), “Exploring the Impact of ChatGPT Literacy on User Satisfaction: The Mediating Role of User Motivations”, Cyberpsychology Behavior and Social Networking, 26(12), 913-918. https://doi.org/10.1089/cyber.2023.0312
Li, X. Y., Zhu, Q. H. & Zhao, Y. (2021), “Research on the Wechat Information Sharing Behavior of the Elderly”, Journal of Modern Information, 41(7), 74-84. https://doi.org/10.3969/j.issn.1008-0821.2021.07.007
Lankton, N. K., Wilson, E. V. & Mao, E. (2010), “Antecedents and determinants of information technology habit”, Information & Management, 47(5-6), 300-307. https://doi.org/10.1016/j.im.2010.06.004
Ma, J. J., Wang, P. C., Li, B. Q., Wang, T., Pang, X. S. & Wang, D. K. (2025), “Exploring User Adoption of ChatGPT: A Technology Acceptance Model Perspective”, International Journal of Human-Computer Interaction, 41(2), 1431-1445. https://doi.org/10.1080/10447318.2024.2314358
Marasinghe, I. K., Weerasooriya, W. A. & Rathnabahu, N. (2024), “Behavioral intention to use electronic resources by distance learners: An extension of the technology acceptance model”, Journal of Librarianship and Information Science, 56(3), 594-606. https://doi.org/10.1177/09610006231154538.
Marshall, R. F., Mallem, K., Xu, H. N., Thorne, J., Burkholder, B., Chaon, B., Liberman, P. & Berkenstock, M. (2024), “Investigating the Accuracy and Completeness of an Artificial Intelligence large language model About Uveitis: An Evaluation of ChatGPT”, Ocular Immunology and Inflammation, 32(9), 2052-2055. https://doi.org/10.1080/09273948.2024.2317417
Nadiv, R. & Kuna, S. (2025), “Bounded professionalism nexus: HR professionalism within and across organizational boundaries”, Human Resource Management Journal, 35(2), 518-538. https://doi.org/10.1111/1748-8583.12577
Nash, B. L. (2024), “Love and Learning in the Age of Algorithms: How Intimate Relationships with Artificial Intelligence May Shape Epistemology, Sociality, and Linguistic Justice”, Reading Research Quarterly, 59(4), 624-631. https://doi.org/10.1002/rrq.549
Nielsen, A., Skylaki, S., Norkute, M. & Stremitzer, A. (2024), “Building a better lawyer: Experimental evidence that artificial intelligence can increase legal work efficiency”, Journal of Empirical Legal Studies, 21(4), 979-1022. https://doi.org/10.1111/jels.12396
O'Leary, D. E. (2024), “Do large language models Bias Human Evaluations?”, IEEE Intelligent Systems, 39(4), 83-87. https://doi.org/10.1109/MIS.2024.3415208
Ohlsson, A. C., Li, Y., Gustavsson, I., Hofling, K., Wahle, U., Osterlind, C. & Iwarsson, J. (2024), “Voice Therapy Outcome: A Comparison Between Imitation Model Voice Therapy and Verbal Instructions Model Voice Therapy”, Journal of Voice, 38(4), 903-910. https://doi.org/10.1016/j.jvoice.2022.01.018
Orwig, W., Edenbaum, E. R., Greene, J. D. & Schacter, D. L. (2024), “The Language of Creativity: Evidence from Humans and large language models”, Journal of Creative Behavior, 58(1), 128-136. https://doi.org/10.1002/jocb.636
Pataranutaporn, P., Liu, R., Finn, E. & Maes, P. (2023), “Influencing human-AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectiveness”, Nature Machine Intelligence, 5(10), 1076-1086. https://doi.org/10.1038/s42256-023-00720-7
Qian, T. Y., Li, W. Z., Gong, H., Seifried, C. & Xu, C. L. (2025), “Experience is all you need: a large language model application of fine-tuned GPT-3.5 and RoBERTa for aspect-based sentiment analysis of college football stadium reviews”, Sport Management Review, 28(1), 1-25. https://doi.org/10.1080/14413523.2024.2386467
Qiu, J. P., Long, K. & Xu, Z. Y. (2025), “Empirical Research of Generative AI Users’ Continuance Use Intention Based on ECT-U&G——In Case of College Students”, Journal of Modern Information, 45(6), 46-59. https://doi.org/10.3969/j.issn.1008-0821.2025.06.005
Qiu, K. H., Bakirtzis, S., Wassell, I., Song, H., Zhang, J. & Wang, K. Z. (2024), “ large language model-Based Wireless Network Design”, IEEE Wireless Communications Letters, 13(12), 3340-3344. https://doi.org/10.1109/LWC.2024.3462556
Sarumi, O. A. & Heider, D. (2024), “ large language models and their applications in bioinformatics”, Computational and Structural Biotechnology Journal, 23, 3498-3505. https://doi.org/10.1016/j.csbj.2024.09.031
Scheepens, D., Millard, J., Farrell, M. & Newbold, T. (2024), “ large language models help facilitate the automated synthesis of information on potential pest controllers”, Methods in Ecology and Evolution, 15(7), 1261-1273. https://doi.org/10.1111/2041-210X.14341
Shivdas, A., Menon, D. G. & Nair, C. S. (2020), “Antecedents of acceptance and use of a digital library system Experience from a Tier 3 Indian city”, The Electronic Library, 38(1), 170-185. https://doi.org/10.1108/EL-03-2019-0074
Statista (2024), “ large language models (LLMs) - statistics & facts”, available at: https://www.statista.com/topics/12691/large-language-models-llms/#topicOverview (Archived by the Internet Archive at https://bit.ly/4kDHvj2)
Straub, D. & Gefen, D. (2004), “Validation guidelines for IS positivist research”, Communications of the Association for Information Systems, 13(1), 380-427. https://doi.org/10.17705/1CAIS.01324
Uddin, M. A., Mahmood, M., Hwang, H. J. & Ostrovskiy, A. (2021), “Can Social Networks Improve User Subjective Wellbeing? Role of Passion and Personality Traits”, Journal of Global Information Management, 29(4), 53-77. https://doi.org/10.4018/JGIM.20210701.oa3
Workman, A. D., Rathi, V. K., Lerner, D. K., Palmer, J. N., Adappa, N. D. & Cohen, N. A. (2024), “Utility of a LangChain and OpenAI GPT-powered chatbot based on the international consensus statement on allergy and rhinology: Rhinosinusitis”, International Forum of Allergy & Rhinology, 14(6), 1101-1109. https://doi.org/10.1002/alr.23310
Wu, J. M. & Holsapple, C. (2014), “Imaginal and emotional experiences in pleasure-oriented IT usage: A hedonic consumption perspective”, Information & Management, 51(1), 80-92. https://doi.org/10.1016/j.im.2013.09.003
Wu, X. Y. & Zhang, D. W. (2023), “The Impact Mechanism of Mobile Visual Search Continuous Behavior Intention from Academic New Media Users: Empirical Analysis of UTAUT2-ECT Integration Model”, Journal of Intelligence, 42(8), 164-176. https://doi.org/10.3969/j.issn.1002-1965.2023.08.025
Xie, J., Zhang, H. & Shi, Q. (2025), “A Study on the Correlation Factors of Psychological Resilience and Impact on AIGC Users’ Dropout Behavior Based on ISM-MICMAC”, Journal of Information Resources Management, 15(1), 126-138. https://doi.org/10.13365/j.jirm.2025.01.126
Xie, P. J & Liu, B. Q. (2024), “Probing Fundamental Visual Comprehend Capabilities on Vision Language Models via Visual Phrases from Structural Data”, Cognitive Computation, 16(6), 3484-3504. https://doi.org/10.1007/s12559-024-10351-8
Xue, Y. J., Dong, Y. & Pu, X. J. (2021), “Model Construction and Empirical Research on Users’ Intention to Continue Using Knowledge Payment Apps”, Economy and Management, 35(4), 17-23.
Yang, Y. Y. & Bao, W. (2025), “Application of Human-Computer Interaction Technology in Remote Language Learning Platform”, International Journal of Human-computer Interaction, 41(3), 1751-1761. https://doi.org/10.1080/10447318.2023.2194709
Yang, Z. W., Zhou, Q. S., Chiu, D. K. & Wang, Y. Q. (2022), “Exploring the factors influencing continuous usage intention of academic social network sites”, Online Information Review, 46(7), 1225-1241. https://doi.org/10.1108/OIR-01-2021-0015
Yazici, H. J. (2025), “Learner acceptance of video conferencing technologies and e-professionalism”, Education and Information Technologies, 30(2), 1821-1847. https://doi.org/10.1007/s10639-024-12880-z
Zhai, R. R. & Han, Z. B. (2024), “Research on the Driving Factors of User Information Interaction in Online Health Communities”, Library and Information Service, 68(3), 15-26. https://doi.org/10.13266/j.issn.0252-3116.2024.03.002
Zhai, S. S., Chen, H. & Wang, Z. R. (2022), “The Influencing Mechanism of Users’ Continuous Usage Intention of AI Learning Platform Based on SES Differences”, Information Science, 40(2), 28-35. https://doi.org/10.13833/j.issn.1007-7634.2022.02.004
Zhang, Q., Liu, Z. Q. & Pan, S. R. (2025), “The Rise of Small Language Models”, IEEE Intelligent Systems, 40(1), 30-37. https://doi.org/10.1109/MIS.2024.3517792
Zhang, T. Y., Koutsoumpis, A., Oostrom, J. K., Holtrop, D., Ghassemi, S. & de Vries, R. E. (2024), “Can Large Language Models Assess Personality From Asynchronous Video Interviews? A Comprehensive Evaluation of Validity, Reliability, Fairness, and Rating Patterns”, IEEE Transactions on Affective Computing, 15(3), 1769-1785 https://doi.org/10.1109/TAFFC.2024.3374875
Zhang, Z. Q., Zhang, Z. L. & Chen, P. Y. (2021), “Early Bird Versus Late Owl: An Empirical Investigation of Individual Shopping Time Habits and its Effects”, MIS Quarterly, 45(1), 117-162. https://doi.org/10.25300/MISQ/2021/14312
Zheng, Y. X., Gan, W. S., Chen, Z. F., Qi, Z. L., Liang, Q. & Yu, P. S. (2025), “Large Language Models for medicine: a survey”, International Journal of Machine Learning and Cybernetics, 16(2), 1015-1040. https://doi.org/10.1007/s13042-024-02318-w
Zhu, Y. M., Zhu, C. F., Wu, T., Wang, S. L., Zhou, Y. Y., Chen, J. Y., Wu, F. & Li, Y. (2025), “Impact of assignment completion assisted by Large Language Model-based chatbot on middle school students’ learning”, Education and Information Technologies, 30(2), 2429-2461. https://doi.org/10.1007/s10639-024-12898-3
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Shuting Yu, Jian Cheng, Jie Cheng, Yakai Gong
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
