{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:33:31Z","timestamp":1776101611140,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"University of Liechtenstein"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This study examines how humans interact with large language models (LLMs) in real-world, unconstrained settings, focusing on potential shifts in users\u2019 mental models. Initially, many users approach LLMs as traditional software tools, employing structured, machine-like prompts. However, after their first interaction, a notable shift occurs, such as increased politeness, more natural language phrasing, and shorter, more contextually nuanced prompts. That is, users increasingly adopt conversational behaviors typical of human-to-human communication and, in turn, this suggests a cognitive transition in the way users perceive and engage with AI systems. Analyzing over 200,000 conversations with computational linguistics methods, we find initial indications supporting this change. These insights have implications for AI design, trust, and ethical concerns, highlighting the need for further research beyond a mostly computational perspective to strengthen our findings on how users cognitively frame their interactions with AI.<\/jats:p>","DOI":"10.1007\/s10844-025-00960-6","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T23:51:24Z","timestamp":1750895484000},"page":"1737-1752","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Mental model shifts in human-LLM interactions"],"prefix":"10.1007","volume":"63","author":[{"given":"Johannes","family":"Schneider","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"issue":"2","key":"960_CR1","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1080\/1463922X.2022.2061080","volume":"24","author":"RW Andrews","year":"2023","unstructured":"Andrews, R. W., Lilly, J. M., Srivastava, D., et al. (2023). The role of shared mental models in human-ai teams: A theoretical review. Theoretical Issues in Ergonomics Science, 24(2), 129\u2013175. https:\/\/doi.org\/10.1080\/1463922X.2022.2061080","journal-title":"Theoretical Issues in Ergonomics Science"},{"key":"960_CR2","unstructured":"Bansal, S. (2021). textstat: Python package to calculate statistics from text. Accessed 07 Sept 2024. https:\/\/pypi.org\/project\/textstat\/"},{"key":"960_CR3","unstructured":"Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with python. Sebastopol, CA: O\u2019Reilly Media Inc.. http:\/\/www.nltk.org\/book_1ed\/"},{"key":"960_CR4","doi-asserted-by":"publisher","unstructured":"Boyd, R. L., Ashokkumar, A., Seraj, S., et al. (2022). The development and psychometric properties of liwc-22. University of Texas at Austin. https:\/\/doi.org\/10.13140\/RG.2.2.21664.87047","DOI":"10.13140\/RG.2.2.21664.87047"},{"key":"960_CR5","doi-asserted-by":"publisher","unstructured":"Brackel-Schmidt, C., Ku\u010devi\u0107, E., Memmert, L., et al. (2023). A user-centric taxonomy for conversational generative language models. Proceedings of the 44th International Conference on Information Systems (ICIS). https:\/\/doi.org\/10.17705\/1icis.2023.01010","DOI":"10.17705\/1icis.2023.01010"},{"key":"960_CR6","unstructured":"Chen, L. (2021). AI chatbot becoming comforting companion in China for the lonely. Accessed 02 Sept 2024. https:\/\/techxplore.com\/news\/2021-08-ai-chatbot-comforting-china-lonely.html"},{"key":"960_CR7","doi-asserted-by":"publisher","unstructured":"Chung, C. K., & Pennebaker, J. W. (2007). The psychological functions of function words. In: Fiedler, K. (Ed.), Social Communication (pp. 343\u2013359). New York, NY: Psychology Press. https:\/\/doi.org\/10.4324\/9780203837702-15","DOI":"10.4324\/9780203837702-15"},{"key":"960_CR8","unstructured":"Danescu-Niculescu-Mizil, C., Sudhof, M., Jurafsky, D., et al. (2013). A computational approach to politeness with application to social factors. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 250\u2013259). Sofia, Bulgaria: Association for Computational Linguistics. https:\/\/aclanthology.org\/P13-1025\/"},{"key":"960_CR9","doi-asserted-by":"publisher","unstructured":"Eigner, E., & H\u00e4ndler, T. (2024). Determinants of llm-assisted decision-making. https:\/\/doi.org\/10.48550\/arXiv.2402.17385. arXiv:2402.17385","DOI":"10.48550\/arXiv.2402.17385"},{"issue":"3","key":"960_CR10","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1037\/h0057532","volume":"32","author":"R Flesch","year":"1948","unstructured":"Flesch, R. (1948). A new readability yardstick. Journal of Applied Psychology, 32(3), 221\u2013233. https:\/\/doi.org\/10.1037\/h0057532","journal-title":"Journal of Applied Psychology"},{"key":"960_CR11","doi-asserted-by":"publisher","unstructured":"Gao, J., Gebreegziabher, S. A., Choo, K. T. W., et al. (2024). A taxonomy for human-llm interaction modes: An initial exploration. In CHI conference on human factors in computing systems. https:\/\/doi.org\/10.1145\/3613905.3650786","DOI":"10.1145\/3613905.3650786"},{"key":"960_CR12","volume-title":"The unwritten rules of social relationships","author":"T Grandin","year":"2005","unstructured":"Grandin, T., Barron, S., & Zysk, V. (2005). The unwritten rules of social relationships. Arlington, Texas: Future Horizons."},{"key":"960_CR13","doi-asserted-by":"publisher","first-page":"113515","DOI":"10.1016\/j.dss.2021.113515","volume":"144","author":"GM Grimes","year":"2021","unstructured":"Grimes, G. M., Schuetzler, R. M., & Giboney, J. S. (2021). Mental models and expectation violations in conversational ai interactions. Decision Support Systems, 144, 113515. https:\/\/doi.org\/10.1016\/j.dss.2021.113515","journal-title":"Decision Support Systems"},{"issue":"5","key":"960_CR14","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1080\/0960085X.2020.1814680","volume":"29","author":"J Hacker","year":"2020","unstructured":"Hacker, J., Vom Brocke, J., Handali, J., et al. (2020). Virtually in this together-how web-conferencing systems enabled a new virtual togetherness during the covid-19 crisis. European Journal of Information Systems, 29(5), 563\u2013584. https:\/\/doi.org\/10.1080\/0960085X.2020.1814680","journal-title":"European Journal of Information Systems"},{"key":"960_CR15","doi-asserted-by":"publisher","unstructured":"Holterman, B., & Deemter, K. (2023). Does chatgpt have theory of mind? https:\/\/doi.org\/10.48550\/arXiv.2305.14020. arXiv:2305.14020","DOI":"10.48550\/arXiv.2305.14020"},{"key":"960_CR16","doi-asserted-by":"publisher","unstructured":"Jakesch, M., Bhat, A., Buschek, D., et al. (2023). Co-writing with opinionated language models affects users\u2019 views. In Proceedings of the 2023 CHI conference on human factors in computing systems. https:\/\/doi.org\/10.1145\/3544548.3581196","DOI":"10.1145\/3544548.3581196"},{"key":"960_CR17","doi-asserted-by":"publisher","unstructured":"Jones, C. R., & Bergen, B. K. (2024). People cannot distinguish gpt-4 from a human in a turing test. https:\/\/doi.org\/10.48550\/arXiv.2405.08007. arXiv:2405.08007","DOI":"10.48550\/arXiv.2405.08007"},{"key":"960_CR18","doi-asserted-by":"publisher","unstructured":"K\u00f6pf, A., Kilcher, Y., R\u00fctte, D., et al. (2024). Openassistant conversations \u2013 democratizing large language model alignment. Advances in neural information processing systems (vol. 36). https:\/\/doi.org\/10.48550\/arXiv.2304.07327","DOI":"10.48550\/arXiv.2304.07327"},{"key":"960_CR19","doi-asserted-by":"publisher","unstructured":"Kumar, H., Musabirov, I., Reza, M., Shi, J., Kuzminykh, A., Williams, J. J., & Liut, M. (2023). Impact of guidance and interaction strategies for llm use on learner performance and perception. https:\/\/doi.org\/10.48550\/arXiv.2310.13712. arXiv:2310.13712","DOI":"10.48550\/arXiv.2310.13712"},{"key":"960_CR20","doi-asserted-by":"publisher","unstructured":"Liu, Y., Cao, J., Liu, C., Ding, K., et al. (2024). Datasets for large language models: A comprehensive survey. https:\/\/doi.org\/10.48550\/arXiv.2402.18041. arXiv:2402.18041","DOI":"10.48550\/arXiv.2402.18041"},{"key":"960_CR21","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.obhdp.2018.12.005","volume":"151","author":"JM Logg","year":"2019","unstructured":"Logg, J. M., Minson, J. A., & Moore, D. A. (2019). Algorithm appreciation: People prefer algorithmic to human judgment. Organizational Behavior and Human Decision Processes, 151, 90\u2013103. https:\/\/doi.org\/10.1016\/j.obhdp.2018.12.005","journal-title":"Organizational Behavior and Human Decision Processes"},{"key":"960_CR22","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann, H. B., & Whitney, D. R. (1947). On a test of whether one of two random variables is stochastically larger than the other. The Annals of Mathematical Statistics, 18, 50\u201360. https:\/\/doi.org\/10.1214\/aoms\/1177730491","journal-title":"The Annals of Mathematical Statistics"},{"key":"960_CR23","unstructured":"Meske, C., Junglas, I., Schneider, J., et al. (2019). How social is your social network? Toward a measurement model. In Proceedings of the 40th International Conference on Information Systems (ICIS), Munich, Germany."},{"key":"960_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-024-00915-3","author":"D Mou","year":"2025","unstructured":"Mou, D., Wei, Z., Ni, L., et al. (2025). Llm-enhanced representation learning for graph collaborative filtering recommendation models. Journal of Intelligent Information Systems. https:\/\/doi.org\/10.1007\/s10844-024-00915-3","journal-title":"Journal of Intelligent Information Systems"},{"issue":"1","key":"960_CR25","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1111\/0022-4537.00153","volume":"56","author":"C Nass","year":"2000","unstructured":"Nass, C., & Moon, Y. (2000). Machines and mindlessness: Social responses to computers. Journal of Social Issues, 56(1), 81\u2013103. https:\/\/doi.org\/10.1111\/0022-4537.00153","journal-title":"Journal of Social Issues"},{"key":"960_CR26","unstructured":"Norman, D. A. (2013). The design of everyday things: Revised and expanded edition. New York: Basic Books."},{"key":"960_CR27","doi-asserted-by":"publisher","unstructured":"Omidvar\u00a0Tehrani, B., & Anubhai, A. (2024). Evaluating human-AI partnership for llm-based code migration. In Extended abstracts of the CHI conference on human factors in computing systems (pp. 133\u201311338). https:\/\/doi.org\/10.1145\/3613905.3650896. https:\/\/dl.acm.org\/doi\/10.1145\/3613905.3650896","DOI":"10.1145\/3613905.3650896"},{"key":"960_CR28","unstructured":"OpenAI (2023). OpenAI moderation system. https:\/\/platform.openai.com\/docs\/guides\/moderation. Accessed 13 Apr 2025"},{"key":"960_CR29","doi-asserted-by":"publisher","unstructured":"Ouyang, S., Wang, S., Liu, Y., Zhong, M., Jiao, Y., et al. (2023). The shifted and the overlooked: A task-oriented investigation of user-gpt interactions. In Proceedings of the 2023 conference on empirical methods in natural language processing. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.146","DOI":"10.18653\/v1\/2023.emnlp-main.146"},{"key":"960_CR30","doi-asserted-by":"publisher","unstructured":"Prather, J., Reeves, B. N., Denny, P., Becker, B. A., et al. (2023). \u201cit\u2019s weird that it knows what i want\u201d: Usability and interactions with copilot for novice programmers. ACM Transactions on Computer-Human Interaction,31(1), 1\u201331. https:\/\/doi.org\/10.1145\/3617367","DOI":"10.1145\/3617367"},{"key":"960_CR31","doi-asserted-by":"publisher","unstructured":"Reeves, B., & Nass, C. (1996). The media equation: How people treat computers, television, and new media like real people and places. New York: Cambridge University Press. https:\/\/doi.org\/10.1017\/CBO9780511751560","DOI":"10.1017\/CBO9780511751560"},{"issue":"1","key":"960_CR32","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1108\/09696471311288519","volume":"20","author":"L Rook","year":"2013","unstructured":"Rook, L. (2013). Mental models: A robust definition. The Learning Organization, 20(1), 38\u201347. https:\/\/doi.org\/10.1108\/09696471311288519","journal-title":"The Learning Organization"},{"key":"960_CR33","unstructured":"RyokoAI (2024). ShareGPT52K. Hugging face. Accessed 03 Sept 2024"},{"key":"960_CR34","doi-asserted-by":"publisher","unstructured":"Sandler, M., Choung, H., Ross, A., & David, P. (2024). A linguistic comparison between human and chatgpt-generated conversations. https:\/\/doi.org\/10.48550\/arXiv.2401.16587. arXiv:2401.16587","DOI":"10.48550\/arXiv.2401.16587"},{"key":"960_CR35","doi-asserted-by":"publisher","unstructured":"Schneider, J., Haag, S., & Kruse, L. C. (2023). Negotiating with llms: Prompt hacks, skill gaps, and reasoning deficits. https:\/\/doi.org\/10.48550\/arXiv.2312.03720. arXiv:2312.03720","DOI":"10.48550\/arXiv.2312.03720"},{"key":"960_CR36","doi-asserted-by":"publisher","unstructured":"Schneider, J., Kilic, S., & Stockhammer, D. (2024). Empowering clients: Transformation of design processes due to generative ai. https:\/\/doi.org\/10.48550\/arXiv.2411.15061. arXiv:2411.15061","DOI":"10.48550\/arXiv.2411.15061"},{"issue":"11","key":"960_CR37","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s10462-024-10916-x","volume":"57","author":"J Schneider","year":"2024","unstructured":"Schneider, J. (2024). Explainable Generative AI (GenXAI): A survey, conceptualization, and research agenda. Artificial Intelligence Review, 57(11), 289. https:\/\/doi.org\/10.1007\/s10462-024-10916-x","journal-title":"Artificial Intelligence Review"},{"key":"960_CR38","unstructured":"ShareGPT (2024). ShareGPT: Share your wildest ChatGPT conversations with one click. https:\/\/sharegpt.com\/. Accessed: 01 June 2024"},{"key":"960_CR39","doi-asserted-by":"publisher","unstructured":"Sharma, A., Rao, S., Brockett, C., et al. (2024). Investigating agency of llms in human-ai collaboration tasks. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL) (pp. 1968\u20131987). https:\/\/doi.org\/10.18653\/v1\/2024.eacl-long.119. https:\/\/aclanthology.org\/2024.eacl-long.119\/","DOI":"10.18653\/v1\/2024.eacl-long.119"},{"key":"960_CR40","doi-asserted-by":"publisher","unstructured":"Shi, J., Jain, R., Doh, H., Suzuki, R., et al. (2023). An hci-centric survey and taxonomy of human-generative-ai interactions. https:\/\/doi.org\/10.48550\/arXiv.2310.07127. arXiv:2310.07127","DOI":"10.48550\/arXiv.2310.07127"},{"key":"960_CR41","doi-asserted-by":"publisher","DOI":"10.1177\/17456916231181102","author":"M Steyvers","year":"2023","unstructured":"Steyvers, M., & Kumar, A. (2023). Three challenges for ai-assisted decision-making. Perspectives on Psychological Science. https:\/\/doi.org\/10.1177\/17456916231181102","journal-title":"Perspectives on Psychological Science"},{"issue":"1","key":"960_CR42","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1177\/0261927X09351676","volume":"29","author":"YR Tausczik","year":"2010","unstructured":"Tausczik, Y. R., & Pennebaker, J. W. (2010). The psychological meaning of words: Liwc and computerized text analysis methods. Journal of Language and Social Psychology, 29(1), 24\u201354. https:\/\/doi.org\/10.1177\/0261927X09351676","journal-title":"Journal of Language and Social Psychology"},{"key":"960_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-024-00915-3","author":"Y Wang","year":"2024","unstructured":"Wang, Y., Shi, X., & Zhao, X. (2024). Mllm4rec: Multimodal information enhancing llm for sequential recommendation. Journal of Intelligent Information Systems. https:\/\/doi.org\/10.1007\/s10844-024-00915-3","journal-title":"Journal of Intelligent Information Systems"},{"key":"960_CR44","doi-asserted-by":"publisher","unstructured":"Yin, T. (2024). Has the use of ai-translated live captions in simultaneous interpreting changed the role of the interpreter? A study based on professional interpreters\u2019 perceptions. The Translator, 1\u201318. https:\/\/doi.org\/10.1080\/13556509.2024.2412923","DOI":"10.1080\/13556509.2024.2412923"},{"key":"960_CR45","doi-asserted-by":"publisher","unstructured":"Zamfirescu-Pereira, J., Wong, R. Y., Hartmann, B., et al. (2023). Why johnny can\u2019t prompt: how non-ai experts try (and fail) to design llm prompts. In Proc. CHI conference on human factors in computing systems. https:\/\/doi.org\/10.1145\/3544548.3581388","DOI":"10.1145\/3544548.3581388"},{"key":"960_CR46","doi-asserted-by":"publisher","unstructured":"Zhao, W., Ren, X., Hessel, J., et al. (2024). Wildchat: 1m chatgpt interaction logs in the wild. https:\/\/doi.org\/10.48550\/arXiv.2405.01470. arXiv:2405.01470","DOI":"10.48550\/arXiv.2405.01470"},{"key":"960_CR47","doi-asserted-by":"publisher","unstructured":"Zheng, L., Chiang, W. -L., Sheng, Y., Li, T., et al. (2023). Lmsys-chat-1m: A large-scale real-world llm conversation dataset. https:\/\/doi.org\/10.48550\/arXiv.2309.11998. arXiv:2309.11998","DOI":"10.48550\/arXiv.2309.11998"},{"issue":"1","key":"960_CR48","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/coli_a_00368","volume":"46","author":"L Zhou","year":"2020","unstructured":"Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2020). The design and implementation of xiaoice, an empathetic social chatbot. Computational Linguistics, 46(1), 53\u201393. https:\/\/doi.org\/10.1162\/coli_a_00368","journal-title":"Computational Linguistics"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-00960-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-025-00960-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-00960-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:17:24Z","timestamp":1759234644000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-025-00960-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["960"],"URL":"https:\/\/doi.org\/10.1007\/s10844-025-00960-6","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,26]]},"assertion":[{"value":"16 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}