Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance
Open accessThe DOI matches its Crossref record; 135 of the 139 references it cites were found in a registry or an index.
Abstract
If a user is presented an AI system that portends to explain how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? This question entails some key concepts of measurement such as explanation goodness and trust. We present methods for enabling developers and researchers to: (1) Assess the a priori goodness of explanations, (2) Assess users' satisfaction with explanations, (3) Reveal user's mental model of an AI system, (4) Assess user's curiosity or need for explanations, (5) Assess whether the user's trust and reliance on the AI are appropriate, and finally, (6) Assess how the human-XAI work system performs. The methods we present derive from our integration of extensive research literatures and our own psychometric evaluations. We point to the previous research that led to the measurement scales which we aggregated and tailored specifically for the XAI context. Scales are presented in sufficient detail to enable their use by XAI researchers. For Mental Model assessment and Work System Performance, XAI researchers have choices. We point to a number of methods, expressed in terms of methods' strengths and weaknesses, and pertinent measurement issues.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605 · cited 2×
“Trust in computers is typically understood in terms of the metaphor of “calibration” (Lee and See, 2004).”
BackgroundConflict, arousal, and curiosity.
Berlyne, D. E. (1960) · McGraw-Hill Book Company · doi:10.1037/11164-000 · Cited by 5,995 · cited 1×
“Epistemic curiosity is the general desire for knowledge, a motive to learn new ideas, resolve knowledge gaps, and solve problems, even though this may entail effortful cognitive activity (Berlyne, 1960, 1978; Loewenstein, 1994; Litman and Lunsford, 2010).”
BackgroundCognitive Reflection and Decision Making
Frederick, S. (2005) · Journal of Economic Perspectives · doi:10.1257/089533005775196732 · Cited by 5,256
Categorization and Representation of Physics Problems by Experts and Novices*
Chi, M. T. H., Feltovich, P. J., & Glaser, R. (1981) · Cognitive Science · doi:10.1207/s15516709cog0502_2 · Cited by 5,248 · cited 1×
“The review article by van der Veer and Melguzio (2003) highlights this method (see also Chi et al., 1981; Evans et al., 2001; St-Cyr and Burns, 2002; van der Veer and Melguzio, 2003).”
Novak, J. D., Gowin, D. B., & Kahle, J. B. (1984) · doi:10.1017/cbo9781139173469 · Cited by 5,199
Mental Models: Towards a Cognitive Science of Language, Inference, and Consciousness
Ford, M., & Johnson-Laird, P. N. (1985) · Language · doi:10.2307/414498 · Cited by 4,419 · cited 2×
“There is a consensus that mental models can be inferred from empirical evidence (Johnson-Laird, 1983; Zhang and Wickens, 1987; Glenberg and Langston, 1992; Qin and Simon, 1992; Bogacz and Trafton, 2004; Clement, 2004; Heiser and Tversky, 2006; Klein and Hoffman, 2008).”
BackgroundThe Efficient Assessment of Need for Cognition
Cacioppo, J. T., Petty, R. E., & Feng Kao, C. (1984) · Journal of Personality Assessment · doi:10.1207/s15327752jpa4803_13 · Cited by 2,913 · cited 1×
“, 2004), Cacioppo’s Need for Cognition scale (Cacioppo et al., 1984), and the I-Type/D-Type Curiosity Scales (Litman and Jimerson, 2004) consider curiosity to be a pervasive style or personality trait.”
BackgroundTrust in Automation: Integrating Empirical Evidence on Factors That Influence Trust
Hoff, K. A., & Bashir, M. (2015) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720814547570 · Cited by 2,817 · cited 2×
“satisfaction: understandability, feeling of satisfaction, sufficiency of detail, completeness, usefulness, accuracy, and trustworthiness (Muir and Moray, 1996).”
BackgroundMethod
Research works printed but not linked: 20
- Adams, 2003, Trust in automated systems
- Biran, 2017, “Explanation and Justification in Machine Learning: A Survey,”, IJCAI-17 Workshop on Explainable Artificial Intelligence (XAI)
- Cañas, 2003, A summary of literature pertaining to the use of concept mapping techniques and technologies for education and performance support
- Carroll, 1984, Minimalist training, Datamation, 1, 125
- Doyle, 2002, “Mental models of dynamic systems,”, System Dynamics and Integrated Modeling, Encyclopedia of Life Support Systems
- Ford, 1993, “Participatory explanation,”, Presented at the FLAIRS 93: Sixth Florida Artificial Intelligence Research Symposium (FLAIRS), 111
- Gentner, 1983, “Flowing waters or teem crowds: Mental models of electricity,”, Mental models, 99
- Gentner, 1983, Mental Models
- Goodstein, 1988, Tasks, errors and mental models.
- Harris, 1984, “Machine intelligence in real systems: Some ergonomic issues,”, Human-Computer Interaction, 267
- Hilton, 1996, Mental models and causal explanation: Judgements of probable cause and explanatory relevance, Thinking Reason., 2, 273, 10.1080/135467896394447 · DOI · Paper page
- Hoffman, 1989, “Whom (or what) do you trust: Historical reflections on the psychology and sociology of information technology,”, Proceedings of the Fourth Annual Symposium on Human Interaction with Complex Systems, 28
- Hoffman, 2018, Literature Review and Integration of Key Ideas for Explainable AI
- Kucala, 2013, The truthiness of trustworthiness., 57
- MillerT. Explanation in artificial intelligence: insights from the social sciences. ArXiv:1706.07269 [Cs]2017 · arXiv
- Ritter, 1988, “Teaching real-time tactical thinking,”, Intelligent Tutoring Systems: Lessons Learned, 285
- Samurcay, 1996, Causal versus topographical support for diagnosis in a dynamic situation, Le Travail Humain, 59, 45
- Sarter, 1997, “Automation surprises,”, Handbook of Human Factors/Ergonomics, 1926
- Taylor, 1988, “Using cognitive models to make plants safer: Experimental and practical approaches,”, Tasks, errors and mental models, 233
- van der Veer, 2003, “Mental models,”, The human-computer interaction handbook, 52
Cited by
Items 101–200 of 277
Explainable AI for cybersecurity decisions: challenges and opportunities
Calvo, A., Preetam, S., & Compastié, M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-329135-7.00018-7 · Cited by 4
eXING-IoT conceptual framework for explainability integration in next generation-IoT
Vultureanu‐Albişi, A., Bădică, C., & Ivanović, M. D. (2025) · Connection Science · doi:10.1080/09540091.2025.2507180 · Cited by 6
How to Validate XAI in Longitudinal Studies?
Gjoreski, M., Laporte, M., Langheinrich, M., & Miller, T. (2024) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3675094.3678997 · Cited by 3
“These constructs are typically measured using dedicated questionnaires adapted from existing questionnaires originally developed for measuring similar constructs, but in different domains (e.g., see Hoffman et al. [11]).”
InfluentialQuid pro Quo: Information disclosure for AI feedback in Human-AI collaboration
Cvetković, I., Grashoff, I., Jovančević, A., & Bittner, E. A. C. (2025) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2025.100137 · Cited by 5
Wang, H., Aligon, J., May, J., Doumard, E., Labroche, N., Delpierre, C., Soulé-Dupuy, C., Casteilla, L., Planat‐Benard, V., & Monsarrat, P. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.04.021 · Cited by 4
Exploring the Interpretability of AI Decision Support Systems for Surgical Anatomy RecognitionPreprint
Khan, D. Z., Adams, T., Wijekoon, A., Herrera, R. R., Bano, S., McCulloch, P. G., Stoyanov, D. V., Clarkson, M. J., Costanza, E., BLANDFORD, A. E., et al. (2026) · medRxiv · doi:10.64898/2026.06.02.26354729 · Cited by 3
Enhancing Trust in Smart Charging Agents—The Role of Traceability for Human-Agent-Cooperation
Attig, C., Schrills, T., Gödker, M., Wollstadt, P., Wiebel-Herboth, C. B., Valdez, A. S. C., & Franke, T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48057-7_19 · Cited by 3
Context Driven Multi-query Resolution Using LLM-RAG to Support the Revision of Explainability Needs
Jayawardena, L., Liret, A., Wiratunga, N., Nkisi-Orji, I., & Fleish, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-96559-3_8 · Cited by 2
Qaadan, S., Alzamer, A., Mohamed, M., Alshare, A., & Schmuelling, B. (2025) · IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) · doi:10.1109/civemsa65862.2025.11084818 · Cited by 2
“This raises questions regarding potential biases or sensitivities inherent to the XAI methods [24], prompting further exploration [28].”
Explainable AI for Visual Inspection: A Comparative Analysis and Review
Albydhany, M. H., & Al‐Darraji, I. (2025) · Journal of Visualized Experiments · doi:10.3791/69440 · Cited by 6
The Enterprising and Elusive Prospects of Human-AI Collaboration
Gadiraju, U., & Balayn, A. (2025) · Springer eBooks · doi:10.1007/978-3-032-01940-0_7 · Cited by 5
Persuasive explanations for recommender systems: how explanations can influence users’ choices?
Rahman, S. M. T., Siemon, D., & Ruotsalo, T. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2025.103720 · Cited by 6
Hein, I., Ullrich, D., & Diefenbach, S. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101025 · Cited by 2
Survey on Explainable AI for Traditional Machine Learning and Domains
Hanif, A., Shawi, R. E., Beheshti, A., & Benatallah, B. (2026) · ACM Computing Surveys · doi:10.1145/3806829 · Cited by 4
“Evaluation in this layer often involves assessing the clarity of narrative explanations, the comprehensibility of model cards [154, 155], and the retention of explanation content over time [103].”
Magalhães, P. C., Arnesen, S., Kern, C. A., König, P. D., Schiff, D. S., & Tyler, T. R. (2026) · Technology in Society · doi:10.1016/j.techsoc.2026.103398 · Cited by 4
Cognitive Readiness for Human-AI Collaboration
Tremblay, S., de Hemptinne, D., Teyssier‐Roberge, G., Gallant, A., Marois, A., & Lafond, D. (2026) · Human Factors The Journal of the Human Factors and Ergonomics Society · doi:10.1177/00187208261474345 · Cited by 5
Divergent impacts of explainable AI for dermatological diagnosis on clinicians versus lay people
Xu, X., Hu, H., Zhang, H., Wang, W. K., Wang, R., Soenksen, L. R., Badri, O., Jafry, S., Burger, E., Nwandu, L., et al. (2026) · Nature Medicine · doi:10.1038/s41591-026-04553-w · Cited by 10
“In addition to the diagnostic tasks of 12 images, participants completed a series of questionnaires, including demographics and established assessments to measure human−AI collaboration experience 62 and AI explanation quality 63 (Supplementary Table.”
Shishakly, R., Khattak, M. N., & Abukhait, R. (2026) · Current Psychology · doi:10.1007/s12144-026-09739-6 · Cited by 3
“Hoffman et al. ( 2023) argued that AI systems can be intentionally designed to trigger curiosity in both users and developers.”
Advancing Edge Artificial Intelligence: System Contexts
Vermesan, O., & Marples, D. (2024) · River Publishers eBooks · doi:10.1201/9781003478713 · Cited by 5
(2024) · International Research Journal of Modernization in Engineering Technology and Science · doi:10.56726/irjmets60972 · Cited by 4
Schwammberger, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73741-1_19 · Cited by 5
“However, purely considering the formal correctness of an explanation is not enough: explanation goodness [12] is a factor that must be considered.”
Empowering Individuals in Automated Decision-Making: Explainability, Contestability and Beyond
Pi, Y. (2024) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3678884.3682043 · Cited by 3
“While these studies focus on gauging people’s understanding [22], satisfaction [11], and trust calibration [16] with various eXplainable AI (XAI) methods, they fails to explore explanations’ abilities to enable pragmatic actions such as challenging an AI decision [15].”
Effects of Presenting Multiple Types of AI Explanations for Visual Task
Maehigashi, A., Fukuchi, Y., & Yamada, S. (2024) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3687272.3688328 · Cited by 3
Beyond conventional adoption: new insights into AI facilitators in Higher Education Institutions
Low, M. P., Soliman, M. S. A., Balushi, M. K. A., & Leong, C. (2025) · Sustainable Futures · doi:10.1016/j.sftr.2025.100781 · Cited by 8
Advancing Edge Artificial Intelligence
Vermesan, O., & Marples, D. (2023) · doi:10.13052/rp-9788770041010 · Cited by 2
Experiential Explanations for Reinforcement Learning
Alabdulkarim, A., Singh, M., Mansi, G., Hall, K., Ehsan, U., & Riedl, M. O. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10951-3 · Cited by 13
“To address RQ3, we thematically analyzed the open-response questions for the tasks and satisfaction survey to better understand how participants used the explanations.”
Johnson, D. S. (2025) · arXiv · doi:10.48550/arxiv.2503.03529 · Cited by 2
Johnson, D. S. (2026) · Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization · doi:10.1145/3774935.3806657 · Cited by 2
Mathur, N., Rahman, H., & Desai, S. (2026) · Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772363.3798685 · Cited by 1
Towards the Design of Explanation-aware Decision Support Systems
Kolajo, T., & Daramola, O. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-73110-5_7 · Cited by 1
Drage, E. (2025) · AI & Society · doi:10.1007/s00146-025-02185-1 · Cited by 3
“(Hoffman et al. 2023).”
"Good" XAI Design: For What? In Which Ways?
Wang, L., Liu, Y., & Goel, A. K. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720036 · Cited by 4
“Increase the ease of use or enjoyment [8, 28] Table 1: User Effects and their definition adapted from Tintarev and Masthoff [55], along with XAI literature that have discusses each effect. of each perception by user participants for each property are also presented in Appendix B.2, Table 8.”
Understanding and Mitigating the Impact of System Failures on Human-Machine Team Performance
Muncie, H., Coetsee, M., & Cameron, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93718-7_20 · Cited by 1
Degen, H., Min, Z., & Nagaraja, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93412-4_3 · Cited by 1
Ghorbanzadeh, D., Rahehagh, A., & Sharbatiyan, M. (2025) · Journal of Systems and Information Technology · doi:10.1108/jsit-06-2024-0217 · Cited by 3
PromptHive: Demonstrating Collaborative, Human-Centered OER Creation with LLMs
Bhandari, S., Anastasopoulos, I., & Pardos, Z. A. (2025) · ACM Conference on Learning @ Scale (L@S) · doi:10.1145/3698205.3733918 · Cited by 1
An Actionability Assessment Tool for Enhancing Algorithmic Recourse in Explainable AI
Singh, R., Miller, T., Sonenberg, L., Velloso, E., Vetere, F., & Howe, P. D. L. (2025) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2025.3582285 · Cited by 16
“…and highlighting the importance of context, this work provides valuable insights for designing more human-centred algorithmic systems to support recourse, and contributes to the growing understanding of how AI-generated explanations can be useful [17], [18].”
Improving Tactical Decision-Making Through Multiobjective Contrastive Explanations
Blom, M. L., Singh, R., Miller, T., Sonenberg, L., Trentelman, K., Saulwick, A., & Wark, S. (2025) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2025.3591163 · Cited by 2
“3) H3: Participants who receive MOCE will be more confi-dentintheirdecisionsandwillratetheirsatisfactionhigheronHoffman’ssatisfactionscale[18].”
Иванович, К. Д., & Lamotkin, A. I. (2025) · FARMAKOEKONOMIKA Modern Pharmacoeconomics and Pharmacoepidemiology · doi:10.17749/2070-4909/farmakoekonomika.2025.328 · Cited by 1
BEE: Belief-Value-Aligned, Explainable, and Extensible Cognitive Framework for Conversational Agents
Yang, C., Groß, M. H., & Wampfler, R. (2025) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3717511.3747067 · Cited by 1
“However, 21.3% had limited knowledge, 17.0% had only basic knowledge, and 4.3% reported no knowledge of LLM-based AI agents.”
InfluentialNon-experts’ Trust in XAI is Unreasonably High
Brdnik, S., Colakovic, I., & Karakatič, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08333-3_9 · Cited by 5
Is attributional style a marker of personification? A case study with ChatGPT
Norcia, M., & Colí, E. (2025) · Journal of Psychology and AI · doi:10.1080/29974100.2025.2569932 · Cited by 1
"Maybe We Need Some More Examples:" Individual and Team Drivers of Developer GenAI Tool Use
Miller, C., Choudhuri, R., Ulloa, M., Haniyur, S., DeLine, R. A., Storey, M.-A., Murphy-Hill, E. R., Bird, C., & Butler, J. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3773155 · Cited by 20
Interpretable World Model Imaginations as Deep Reinforcement Learning Explanation
Wenninghoff, N., & Schwammberger, M. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08327-2_7 · Cited by 3
Fostering Positive Interactions Through Psychological Ownership in Intelligent Systems
Dalangin, B., Gordon, S. M., Roy, H., & Neubauer, C. E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-13184-3_11 · Cited by 1
Analysing User Perceptions of Trust in Financial Systems Using Explainable AI
Mandava, R., Haritha, K., Vellela, S. S., Purimetla, N. R., Mohan, B. K., & Harinadh, T. (2025) · International Conference on Networks and Soft Computing (ICNSoC) · doi:10.1109/icnsoc66817.2025.00018 · Cited by 38
Beyond Algorithms: Human-Centered Explainability for Clinicians, Patients, and Caregivers
Mamun, T. I., Novak, L. L., & Salwei, M. E. (2026) · Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care · doi:10.1177/2327857926151146 · Cited by 1
“Explanations should be evaluated using clarity, usefulness, user satisfaction, mental model accuracy, trust calibration, and human–AI performance (Hoffman et al., 2023; Ibne Mamun et al., 2022; Mamun, Baker, et al., 2021).”
How does contextual fidelity impact how we think, talk, and act in AI-assisted engineering design?
Vyas, S., Cheruku, S., & Krishnamurthy, V. R. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104456 · Cited by 4
Qi, R., Liu, G., Zhang, J., & Hsiao, J. H. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103773 · Cited by 2
Evaluating User Trust in Embodied Conversational Agents for Career Counselling
Sautchuk-Patrício, N., Hettmann, W., Wölfel, M., & Henning, P. A. (2025) · International Conference on Education Technology and Computer · doi:10.1109/icetc66579.2025.11387454 · Cited by 2
“Eloquence was evaluated through an adapted version of the Speech Evaluation Instrument (SEI) [36], while Perceived Explainability was measured using an adapted version of the Explanation Satisfaction Scale (ESS) [37], each comprising six items.”
Zia, M. F., Ouameur, M. A., Bagaa, M., Massicotte, D., & Ksentini, A. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112142 · Cited by 3
Balaskas, S., Komis, K., Yfantidou, I., & Skandali, D. (2026) · Multimodal Technologies and Interaction · doi:10.3390/mti10030022 · Cited by 3
Dojcinovic, S., Strecker, J., Mayer, S., & Bektaş, K. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742413.3789129 · Cited by 1
Dietz, M., Osiander, C., Sirman-Winkler, M., & Tepe, M. (2026) · Public Administration Review · doi:10.1111/puar.70111 · Cited by 3
“Hoffman et al. (2023) provide a comprehensive overview of the challenges of measuring explainability.”
Yadav, S., Kaushik, A., & McDaid, K. (2026) · Applied AI Letters · doi:10.1002/ail2.70028 · Cited by 1
Scala, D. D., & de Boer, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21300-6_8 · Cited by 2
CritiqueCrew: Orchestrating Multi-Perspective Conversational Design Critique
Chen, X., Zhou, J., Shu, Y., Wang, R., & Liu, Q. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791391 · Cited by 4
“For Study2,weadditionallyincludedtheCreativitySupportIn-dex(CSI)[9]tosupportcreativeexploration.”
Wright, L., Legarda, I., Lasa, G., & Escallada, O. (2026) · Open Research Europe · doi:10.12688/openreseurope.22034.1 · Cited by 2
Explain it for Safety: Explanations for Risk Mitigation
Schwammberger, M., Rakow, A., Putze, L., & Bairy, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16855-9_16 · Cited by 1
Sofyan, V. A., Lamada, M. S., Fakhri, M. M., Shiddiq, A. K., & Masna, U. K. (2026) · Asian Education and Development Studies · doi:10.1108/aeds-10-2025-0551 · Cited by 1
Evaluating Explainability: Metrics, Benchmarks, and Human-Centered Evaluation Methods
Yousefi, N., & Zamanifar, A. (2026) · Springer eBooks · doi:10.1007/978-3-032-15088-2_10 · Cited by 1
Advances in explainable artificial intelligence evaluation and ethics from 2023 to 2025
Pujari, J. J., Nayak, R., Putheti, S., Bikku, T., Shanmugasundaram, P., & Thota, S. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01473-z · Cited by 3
“Recent studies [25, 31] have shown that humans tend to favor local explanations, especially if the explanations are actionable, though there is pressure from regulators to focus on global explanations [23, 52].”
InfluentialAttanasio, C., Vilone, G., Holzinger, A., & Longo, L. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2675436 · Cited by 1
A Review of Taxonomies of Explainable AI (XAI) Evaluation
Speith, T. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3806537 · Cited by 3
“Evaluator: Human-Based 28 [17, 28, 51, 67, 69, 77–79, 81, 89, 104, 134, 143–145, 148, 156, 157, 159, 163, 165, 184, 185, 187, 189, 192, 194, 200] Evaluator: Human-Indep.”
User Mental Models as a Lens for Evaluating Explainable-AI System Outputs
Ardito, C. A., Bonis, M. L. N. D., Noia, T. D., Sciascio, E. D., Fasano, G., & Lombardi, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-22934-2_14 · Cited by 1
Brdnik, S., Colakovic, I., & Karakatič, S. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115894 · Cited by 2
Explainable deep learning improves human mental models of self-driving cars
Kenny, E. M., Dharmavaram, A., Lee, S. U., Phan-Minh, T., Rajesh, S., Hu, Y., Major, L., Tomov, M. S., & Shah, J. (2026) · Nature · doi:10.1038/s41586-026-10950-5 · Cited by 7
“Follow-up analyses revealed that the AV stopped for the cyclist due to backup safety mechanisms unrelated to CW-Net, which indicates that the driver’s increased level of caution was appropriate.”
Interactive and Explainable Robot Learning: A Comprehensive Review
Seraj, E., Lee, K. M., Zaidi, Z., Xiao, Q., Li, Z., Nascimento, A., van Waveren, S., Tambwekar, P., Paleja, R., Das, D., et al. (2024) · Foundations and Trends in Robotics · doi:10.1561/2300000081 · Cited by 7
CO-XAI—Cognitive Decision Intelligence Framework for Explainable AI Systems
Sajno, E., Gaspari, S. D., Pupillo, C., & Riva, G. (2024) · Cyberpsychology Behavior and Social Networking · doi:10.1089/cyber.2024.87594.ceu · Cited by 1
Barile, R., d’Amato, C., & Fanizzi, N. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714667 · Cited by 4
“Improving the FSV helps to reinforce user trust in predictions because it reflects how confident they are with the predictive process [16].”
Dynamics of Mental Models: Objective Vs. Subjective User Understanding of a Robot in the Wild
Gebellí, F., Garrell, A., Lemaignan, S., & Ros, R. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3579217 · Cited by 2
“Evaluation of understanding with part of the nursing staff right after the tutorial session and before any usage of the system. the user’s understanding of the robot is often done by analysing those mental models [4].”
InfluentialWang, H., Aligon, J., May, J., Doumard, E., Labroche, N., Delpierre, C., Soulé-Dupuy, C., Casteilla, L., Planat‐Benard, V., & Monsarrat, P. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.04.06.647498 · Cited by 1
“In current XAI evaluations, significant emphasis is placed on application-grounded assessments, notably plausibility [12] and user satisfaction [25].”
Explainable AI as a Double-Edged Sword in Dermatology: The Impact on Clinicians versus The PublicPreprint
Xu, X., Hu, H., Zhang, H., Wang, W. K., Wang, R., Soenksen, L. R., Badri, O., Jafry, S., Burger, E., Nwandu, L., et al. (2025) · medRxiv · doi:10.64898/2025.12.19.25342205 · Cited by 1
Alon, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6172315
Irandoust, H., & Ghajar-Khosravi, S. (2024) · IEEE International Conference on Human-Machine Systems (ICHMS) · doi:10.1109/ichms59971.2024.10555660 · Cited by 1
“…further user studies need to be conducted to evaluate the effectiveness of explanation capabilities from human factors perspectives [26][30][38][44][45], and to study the cross-section of different measures, for example, the impact of explanation effectiveness on the AI performance in…”
BackgroundInfluentialOz, B., Karran, A. J., Boasen, J., Coursaris, C. K., & Léger, P. (2024) · Lecture notes in information systems and organisation · doi:10.1007/978-3-031-58396-4_15 · Cited by 3
Maehigashi, A., Fukuchi, Y., & Yamada, S. (2024) · IEEE RO-MAN · doi:10.1109/ro-man60168.2024.10731272 · Cited by 2
“After completing 30 trials, participants responded to a trust scale for XAI [34] consisting of 8 items on a 5-point scale (1: I strongly agree - 5: I strongly disagree).”
MethodIt’s Safe to Play While Driving: From a Spatial Traffic Logic Towards Traffic Games
Schwammberger, M., & Hamarneh, Q. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-75434-0_19 · Cited by 2
Artificial Intelligence in Design: Its Acceptance Among College Students
Higuera-Trujillo, J. L., Bosch-Mancillas, C. E., Pérez-Chantes, M., & Laija-Arellanes, D. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-3-031-72829-7_42 · Cited by 1
Can We Trust the Actionable Guidance from Explainable AI Techniques in Defect Prediction?
Lee, G., Ju, H., & Lee, S. U.-J. (2025) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner64311.2025.00051 · Cited by 3
Al-Ansari, N., Al‐Thani, D., & Bahameish, M. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101083 · Cited by 2
Kirkpatrick, A. W. (2025) · International Journal of Strategic Communication · doi:10.1080/1553118x.2025.2515277
“The perceived trustworthiness of AI systems was measured according to an 8-item scale adapted from the trust in explainable AI scale (Hoffman et al., 2023).”
A Roadmap Towards Dynamic Conflict Management for Autonomous Traffic Agents⋆
Schwammberger, M. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097779 · Cited by 3
“Explanation validation and explanation goodness is a crucial factor, as is also argued in [45], [46].”
Shahriari, R., Yang, Y., Tamboli, D. N. A., Perez, M., Zha, Y., Hou, J., Deng, M., Ragan, E. D., Ruiz, J., Wang, D. Z., et al. (2025) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2025.3598204 · Cited by 2
“Participants’ satisfaction with the explanations and their trust in the system were both assessed using scales adapted from Hoffman et al. [20], specifically the Explanation Satisfaction Scale and the Trust Scale for the XAI context .”
InfluentialKovesdi, C., Yamani, Y., Jackson, A., & Lin, L. (2025) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/10711813251368829 · Cited by 1
“This proposed framework is being explored as part of a multimethod/ multi-measure approach to evaluate trust, combined with survey-based approaches such as those described in Chancey et al. (2017) and Hoffman et al. (2023).”
PromptHive: Demonstrating Collaborative, Human-Centered OER Creation with LLMs
Pardos, Z. A., Bhandari, S., & Anastasopoulos, I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-03873-9_47
Yao, J., Yan, D., & Zhang, H. (2025) · Computers in Human Behavior · doi:10.1016/j.chb.2025.108793
HollerithProfitML: A Prototype to support the use and comprehensibility of AI for SMEs
Weiss, L., Möhring, M., Dahal, K. P., & Dagne, S. (2025) · International Conference on Software, Knowledge, Information Management and Applications (SKIMA) · doi:10.1109/skima66621.2025.11155350
“During the development phase, however, developing the system in a way designed for the matters of (XAI) is often challenging [13].”
InfluentialSardari, S., Fernandes, F., Araya-Martinez, J. M., Zak, J. A., & Roitberg, A. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11163755 · Cited by 3
“We filtered various characteristics of explainability from prior research [27], [36], [37] to tailor them for industrial use cases, and identified two main categories as follows: Comprehensibility/Interpretability Refers to how under-standable the explanation is to the target audience, encompassing…”
Explaining the inexplicable: a study of people's reactions to futuristic AI
Smith, W., Masters, P., Liu, J., Kuhn, G., & Kelly, R. (2024) · Australian Conference on Human-Computer Interaction (OzCHI) · doi:10.1145/3726986.3727046
“Researchers in explainable and interpretable AI (XAI), one of four fields identified by Capel and Brereton [2] at the intersection of HCI and AI, focus on ways to improve how AI technologies explain themselves, often by making explicit hidden aspects of their decision-making processes [6].”
How Should Your Artificial Teammate Tell You How Much It Trusts You?
Jorge, C. C., Dumitrescu, E., Jonker, C. M., Loghin, R., Marossi, S., Uleia, E., & Tielman, M. L. (2025) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3717511.3747086 · Cited by 1
Onari, M. A., Baer, G. T., Zhang, C., Grau, I., Nobile, M. S., & Zhang, Y. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08317-3_15 · Cited by 4
Assessing and Quantifying Perceived Trust in Interpretable Clinical Decision Support
Onari, M. A., Grau, I., Zhang, C., Nobile, M. S., & Zhang, Y. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-08327-2_10 · Cited by 1
Let’s Talk AI with Business Innovation Expert Ellen Enkel
Enkel, E., & Steffen, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09008-9_3
Kölmel, L., Becker, M., Schwall, F., Hild, J., Birnstill, P., Deml, B., & Beyerer, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5893623
Artificial Intelligence in Nanomanufacturing for Optimizing Design, Fabrication, and Quality Control
Kumar, S., & Singh, H. (2025) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9798898812942125010010
Levels of Explanation for Error Resolution in HRI
Krakovski, M., Kumar, S., & Edan, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-2398-6_36
Lam, W., Wu, W., Chen, Z., & He, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6190607
Li, H., Lou, W., Liu, Y., Chen, H., Bu, L., & Wu, J. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2622589
Empirical Assessment of Software Engineers’ Mental models in the Context of Digital Library SystemsPreprint
Islam, M. H., & Shanto, H. I. (2026) · doi:10.14293/pr2199.002898.v1
Metadata
- Authors
- Hoffman, R. R., Mueller, S. T., Klein, G., & Litman, J.
- Affiliations
- Florida Institute for Human and Machine Cognition (US)
- Michigan Technological University (US)
- University of Maine at Machias (US)
- Corresponding author
- Hoffman, Robert R.
- Venue
- Frontiers in Computer Science
- Publisher
- Frontiers Media SA
- Published
- 2023-02-06
- Volume
- 5
- ISSN
- 2624-9898 (ISSN-L)
- OpenAlex
- W4319321305
- Cited by
- 272
- References
- 139
- Citations by year
- 2026: 117 · 2025: 97 · 2024: 46 · 2023: 12
- FWCI
- 25.64
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Computer Science (publishedVersion, cc-by)
- Digital Commons - Michigan Tech (Michigan Technological University) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Defense Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- explainable AI, user satisfaction, mental models, curiosity, trust in AI, measurement scales, psychometric assessment
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.