Towards Warranted Trust: A Model on the Relation Between Actual and Perceived System Trustworthiness
Loading...
Fulltext URI
Document type
Text/Conference Paper
Additional Information
Date
relationships.isAuthorOf
Journal Title
Journal ISSN
Volume Title
Publisher
ACM
Abstract
The public discussion about trustworthy AI is fueling research on new methods to make AI explainable and fair. However, users may incorrectly assess system trustworthiness and could consequently overtrust untrustworthy systems or undertrust trustworthy systems. In order to understand what determines accurate assessments of system trustworthiness we apply Brunswik’s Lens Model and the Realistic Accuracy Model. The assumption is that the actual trustworthiness of a system cannot be accessed directly and is therefore inferred via cues to form a user’s perceived trustworthiness. The accuracy of trustworthiness assessment then depends on: cue relevance, availability, detection, and utilization. We describe how the model can be used to systematically investigate determinants that increase the match between system’s actual trustworthiness and user’s perceived trustworthiness in order to achieve warranted trust.
Description
Keywords
Trustworthiness, human-centered AI
Citation
Collections
Endorsement
Review
Supplemented By
Referenced By
Number of citations to item: 17
- Andrea Ferrario, Michele Loi (2022): How Explainability Contributes to Trust in AI, In: 2022 ACM Conference on Fairness, Accountability, and Transparency, doi:10.1145/3531146.3533202
- Rodrigo Chacón Quesada, Fernando Estévez Casado, Yiannis Demiris (2025): An Integrated 3D Eye-Gaze Tracking Framework for Assessing Trust in Human–Robot Interaction, In: ACM Transactions on Human-Robot Interaction 3(14), doi:10.1145/3725861
- Roel Visser, Tobias M. Peters, Ingrid Scharlau, Barbara Hammer (2025): Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation, In: Cognitive Systems Research, doi:10.1016/j.cogsys.2025.101357
- Stefan Schmager, Ilias O. Pappas, Polyxeni Vassilakopoulou (2025): Understanding Human-Centred AI: a review of its defining elements and a research agenda, In: Behaviour & Information Technology 15(44), doi:10.1080/0144929x.2024.2448719
- Alison J. Wright, Eva Jermutus, Ella Howes, Alison O'Mara-Eves, Clement Veall, Jennie Ives, Susan Michie (2024): The Artificial Intelligence in Public Health Toolkit: A novel resource for stakeholder engagement, In: Wellcome Open Research, doi:10.12688/wellcomeopenres.22480.1
- Andrea Ferrario, Michele Loi (2022): How Explainability Contributes to Trust in AI, In: SSRN Electronic Journal, doi:10.2139/ssrn.4020557
- Andrew Silva, Pradyumna Tambwekar, Mariah Schrum, Matthew Gombolay (2024): Towards Balancing Preference and Performance through Adaptive Personalized Explainability, In: Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, doi:10.1145/3610977.3635000
- Timo Speith, Barnaby Crook, Sara Mann, Astrid Schomäcker, Markus Langer (2024): Conceptualizing understanding in explainable artificial intelligence (XAI): an abilities-based approach, In: Ethics and Information Technology 2(26), doi:10.1007/s10676-024-09769-3
- Kevin Baum, Sebastian Biewer, Holger Hermanns, Sven Hetmank, Markus Langer, Anne Lauber-Rönsberg, Sarah Sterz (2024): Taming the AI Monster: Monitoring of Individual Fairness for Effective Human Oversight, In: Lecture Notes in Computer Science, doi:10.1007/978-3-031-66149-5_1
- Sebastian Bartsch, Oliver Behn, Alexander Benlian, Roger Brownsword, Sebastian Bücker, Marcus Düwell, Nico Formánek, Marc Jungtäubl, Michael Leyer, Alexander Richter, Jan-Hendrik Schmidt, Mascha Will-Zocholl (2025): Governance of High-Risk AI Systems in Healthcare and Credit Scoring, In: Business & Information Systems Engineering 4(67), doi:10.1007/s12599-025-00944-4
- Siddharth Mehrotra, Chadha Degachi, Oleksandra Vereschak, Catholijn M. Jonker, Myrthe L. Tielman (2024): A Systematic Review on Fostering Appropriate Trust in Human-AI Interaction: Trends, Opportunities and Challenges, In: ACM Journal on Responsible Computing 4(1), doi:10.1145/3696449
- Jakob Schoeffer, Niklas Kuehl, Yvette Machowski (2022): “There Is Not Enough Information”: On the Effects of Explanations on Perceptions of Informational Fairness and Trustworthiness in Automated Decision-Making, In: 2022 ACM Conference on Fairness, Accountability, and Transparency, doi:10.1145/3531146.3533218
- Saleh Afroogh, Ali Akbari, Emmie Malone, Mohammadali Kargar, Hananeh Alambeigi (2024): Trust in AI: progress, challenges, and future directions, In: Humanities and Social Sciences Communications 1(11), doi:10.1057/s41599-024-04044-8
- Julius Wenzel, Maximilian A. Köhl, Sarah Sterz, Hanwei Zhang, Andreas Schmidt, Christof Fetzer, Holger Hermanns (2024): Traceability and Accountability by Construction, In: Lecture Notes in Computer Science, doi:10.1007/978-3-031-75387-9_16
- Markus Langer (2023): Fehlgeleitete Hoffnungen?, In: Psychologische Rundschau 4(74), doi:10.1026/0033-3042/a000626
- Siddharth Mehrotra, Ujwal Gadiraju, Eva Bittner, Folkert van Delden, Catholijn M. Jonker, Myrthe L. Tielman (2025): “Even explanations will not help in trusting [this] fundamentally biased system”: A Predictive Policing Case-Study, In: Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization, doi:10.1145/3699682.3728343
- Nur Efsan Cetinkaya, Nicole Krämer (2025): Between transparency and trust: identifying key factors in AI system perception, In: Behaviour & Information Technology, doi:10.1080/0144929x.2025.2533358