The Illusion of Explanatory Depth in Generative AI: Miscalibration, User Profiles, and the Persistence of Retrieval-Based Mental Models
Open accessThe DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
Mental models of Generative AI (GenAI) shape how users interpret outputs and decide when to verify information, yet users often infer how these systems work from surface behavior rather than mechanistic understanding. Drawing on the illusion of explanatory depth (IoED), this mixed-methods study examined whether perceived understanding changes after an explanation attempt and whether self-evaluations align with demonstrated explanatory understanding. A large adult sample (N = 2,926) rated their understanding of how GenAI produces answers, wrote an open-ended explanation, and then rated their understanding again. Explanations were rubric-scored for explanatory quality and coded for recurring themes. Results showed substantial miscalibration. Self evaluations changed minimally after the explanation attempt (pre M = 3.90; post M = 3.95). In contrast, demonstrated understanding was low (M = 2.20), revealing a large gap between perceived and explanation-based understanding. Explanations were dominated by retrieval-based misconceptions: 54.03% described GenAI as a web search engine and 9.60% as an internal database, whereas mechanistic generative explanations (e.g., token prediction) were rare (2.22%). A two-step cluster analysis identified three user profiles: over-estimators (51.9%) reported high confidence but provided weak, retrieval-framed explanations; calibrated explainers (13.5%) paired high confidence with strong mechanistic accounts; and underconfident low-knowledge participants (34.6%) reported low confidence and also provided weak explanations. These findings suggest that confidence-explanation gaps can persist even after an explanation attempt and that fluent interaction may reinforce familiar search metaphors. The study underscores the need for AI literacy that explicitly contrasts retrieval and generation to support calibrated reliance in human-AI interaction.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
The misunderstood limits of folk science: An illusion of explanatory depth
Rozenblit, L., & Keil, F. (2002) · Cognitive Science · doi:10.1207/s15516709cog2605_1 · Cited by 1,032
Artificial intelligence and illusions of understanding in scientific research
Messeri, L., & Crockett, M. J. (2024) · Nature · doi:10.1038/s41586-024-07146-0 · Cited by 707
The Metacognitive Demands and Opportunities of Generative AI
Tankelevitch, L., Kewenig, V., Simkute, A., Scott, A. E., Sarkar, A., Sellen, A., & Rintel, S. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642902 · Cited by 493
My AI Friend: How Users of a Social Chatbot Understand Their Human–AI Friendship
Brandtzaeg, P. B., Skjuve, M., & Følstad, A. (2022) · Human Communication Research · doi:10.1093/hcr/hqac008 · Cited by 490
Trust and reliance on AI — An experimental study on the extent and costs of overreliance on AI
Klingbeil, A., Grützner, C., & Schreck, P. (2024) · Computers in Human Behavior · doi:10.1016/j.chb.2024.108352 · Cited by 450
Explanations Can Reduce Overreliance on AI Systems During Decision-Making
Vasconcelos, H., Jörke, M., Grunde-McLaughlin, M., Gerstenberg, T., Bernstein, M. S., & Krishna, R. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579605 · Cited by 402
Hornberger, M., Bewersdorff, A., & Nerdel, C. (2023) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2023.100165 · Cited by 276
Hoffman, R. R., Mueller, S. T., Klein, G., & Litman, J. (2023) · Frontiers in Computer Science · doi:10.3389/fcomp.2023.1096257 · Cited by 272
Johnson-Laird, P. N. (1989) · The Foundations of Cognitive Science · doi:10.7551/mitpress/3072.003.0014 · Cited by 230
Three Challenges for AI-Assisted Decision-Making
Steyvers, M., & Kumar, A. (2024) · Perspectives on Psychological Science · doi:10.1177/17456916231181102 · Cited by 217
Panigutti, C., Beretta, A., Giannotti, F., & Pedreschi, D. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502104 · Cited by 215
Andersen, J. P., Degn, L., Fishberg, R., Graversen, E. K., Horbach, S. P. J. M., Schmidt, E. K., Schneider, J. W., & Sørensen, M. P. (2025) · Technology in Society · doi:10.1016/j.techsoc.2025.102813 · Cited by 206
Kim, J. H., Kim, J., Park, J., Kim, C., Jhang, J., & King, B. (2025) · Journal of Travel Research · doi:10.1177/00472875231212996 · Cited by 202
The role of shared mental models in human-AI teams: a theoretical review
Andrews, R. W., Lilly, J. M., Srivastava, D., & Feigh, K. M. (2023) · Theoretical Issues in Ergonomics Science · doi:10.1080/1463922x.2022.2061080 · Cited by 191
Shin, D., Kee, K. F., & Shin, E. Y. (2022) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2022.102494 · Cited by 191
Mills, C. M., & Keil, F. C. (2004) · Journal of Experimental Child Psychology · doi:10.1016/j.jecp.2003.09.003 · Cited by 186
Decisions with ChatGPT: Reexamining choice overload in ChatGPT recommendations
Kim, J., Kim, J. H., Kim, C., & Park, J. (2023) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2023.103494 · Cited by 173
How to explain AI systems to end users: a systematic literature review and research agenda
Laato, S., Tiainen, M., Najmul Islam, A. K. M., & Mäntymäki, M. (2022) · Internet Research · doi:10.1108/intr-08-2021-0600 · Cited by 155
I Think I Get Your Point, AI! The Illusion of Explanatory Depth in Explainable AI
Chromik, M., Eiband, M., Buchner, F., Krüger, A., & Butz, A. (2021) · 26th International Conference on Intelligent User Interfaces · doi:10.1145/3397481.3450644 · Cited by 144
Brauner, P., Hick, A., Philipsen, R., & Ziefle, M. (2023) · Frontiers in Computer Science · doi:10.3389/fcomp.2023.1113903 · Cited by 143
Hendren, K., Newcomer, K., Pandey, S. K., Smith, M., & Sumner, N. (2023) · Public Administration Review · doi:10.1111/puar.13528 · Cited by 130
Dogruel, L., Facciorusso, D., & Stark, B. (2020) · Information Communication & Society · doi:10.1080/1369118x.2020.1863999 · Cited by 128
The Who in XAI: How AI Background Shapes Perceptions of AI Explanations
Ehsan, U., Passi, S., Liao, Q. V., Chan, L., Lee, I.-H., Muller, M., & Riedl, M. O. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642474 · Cited by 123
The illusion of explanatory depth and endorsement of conspiracy beliefs
Vitriol, J. A., & Marsh, J. K. (2018) · European Journal of Social Psychology · doi:10.1002/ejsp.2504 · Cited by 118
User Perception of Recommendation Explanation: Are Your Explanations What Users Need?
Lu, H., Ma, W., Wang, Y., Zhang, M., Wang, X., Liu, Y., Chua, T., & Ma, S. (2022) · ACM Transactions on Information Systems · doi:10.1145/3565480 · Cited by 69
Design Metaphors for Understanding User Expectations of Socially Interactive Robot Embodiments
Dennler, N. S., Ruan, C., Hadiwijoyo, J., Chen, B., Nikolaidis, S., & Matarić, M. J. (2022) · ACM Transactions on Human-Robot Interaction · doi:10.1145/3550489 · Cited by 66
Generative AI in the Wild: Prospects, Challenges, and Strategies
Sun, Y., Jang, E., Ma, F., & Wang, T. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642160 · Cited by 64
Using a Mixed Methods Content Analysis to Analyze Mission Statements From Colleges of Engineering
Creamer, E. G., & Ghoston, M. R. (2012) · Journal of Mixed Methods Research · doi:10.1177/1558689812458976 · Cited by 61
Johnson, J. G., Peralta, M., Kaur, M., Huang, R., Zhao, S. G., Guan, R., Rajaram, S., & Nebeling, M. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757595 · Cited by 40
Liu, Y., & Du, Y. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2465861 · Cited by 37
Mental Models of Generative AI Chatbot Ecosystems
Wang, X., Xiao-zheng, W., Park, S., & Yao, Y. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712125 · Cited by 32
A Scoping Review of Mental Model Research in HCI from 2010 to 2021
Hu, X., & Twidale, M. B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48038-6_7 · Cited by 31
Me vs. the machine? Subjective evaluations of human- and AI-generated advice
Osborne, M. R., & Bailey, E. R. (2025) · Scientific Reports · doi:10.1038/s41598-025-86623-6 · Cited by 30
Search+Chat: Integrating Search and GenAI to Support Users with Learning-oriented Search Tasks
Yang, Y., Urgo, K., Arguello, J., & Capra, R. (2025) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3698204.3716446 · Cited by 29
Building Appropriate Mental Models: What Users Know and Want to Know about an Agentic AI Chatbot
Brachman, M., Kunde, S., Miller, S., Fucs, A., Dempsey, S., Jabbour, J., & Geyer, W. (2025) · Proceedings of the 30th International Conference on Intelligent User Interfaces · doi:10.1145/3708359.3712071 · Cited by 18
Alon, L., Forkosh‐Baruch, A., & Nachmias, R. (2020) · Aslib Journal of Information Management · doi:10.1108/ajim-07-2020-0208 · Cited by 16
Self-citationLv, D., Sun, R., Zhu, Q., & Qin, S. (2025) · BMC Psychology · doi:10.1186/s40359-025-02894-8 · Cited by 13
Don’t Be Fooled: The Misinformation Effect of Explanations in Human–AI Collaboration
Spitzer, P., Holstein, J., Morrison, K., Holstein, K., Satzger, G., & Kühl, N. (2026) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2025.2574511 · Cited by 12
Alcasid, G. A. L., & Haskel‐Ittah, M. (2024) · Research in Science Education · doi:10.1007/s11165-024-10191-4 · Cited by 10
Meyers, E. A., Gretton, J. D., Budge, J. R. C., Fugelsang, J. A., & Koehler, D. J. (2023) · Judgment and Decision Making · doi:10.1017/jdm.2023.24 · Cited by 10
Martínez, C. D. G., & Corredor, J. (2024) · Memory & Cognition · doi:10.3758/s13421-024-01616-6 · Cited by 6
Li, X., Liu, H., Zhou, T., Hu, C., & Ramayah, T. (2026) · Scientific Reports · doi:10.1038/s41598-025-32935-6 · Cited by 4
Alon, L., & Krtalić, M. (2025) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.1305 · Cited by 2
Self-citation
Research works printed but not linked: 3
- Y Elsayed, 2024, ChatGPT and the illusion of explanatory depth, Proceedings of the Annual Meeting of the Cognitive Science Society
- N Vaupoti?, 2022, Gaining insight through explaining? How generating explanations affects individuals' perceptions of their own and of experts' knowledge, International Journal of Science Education, 12, 42
- J Wilson, 2023, Perceptions of explanation completeness help decrease knowledge overestimation, Proceedings of the Annual Meeting of the Cognitive Science Society
Metadata
- Authors
- Alon, L.
- Affiliations
- Tel Hai Academic College (IL)
- Corresponding author
- Alon, Lilach
- ORCID
- Alon, Lilach
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2026
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W7127417011
- Cited by
- 0
- References
- 30
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (acceptedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Psychology › Developmental and Educational Psychology › Educational Strategies and Epistemologies
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- illusion of explanatory depth, generative AI, mental models, calibration error, mechanistic explanation, AI literacy, user profiles, human-AI interaction, explanation quality
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.