The relationship between trust in AI and trustworthy machine learning technologies
Open accessThe DOI matches its Crossref record; 91 of the 91 references it cites were found in a registry or an index.
Abstract
To design and develop AI-based systems that users and the larger public can justifiably trust, one needs to understand how machine learning technologies impact trust. To guide the design and implementation of trusted AI-based systems, this paper provides a systematic approach to relate considerations about trust from the social sciences to trustworthiness technologies proposed for AI-based services and products. We start from the ABI+ (Ability, Benevolence, Integrity, Predictability) framework augmented with a recently proposed mapping of ABI+ on qualities of technologies that support trust. We consider four categories of trustworthiness technologies for machine learning, namely these for Fairness, Explainability, Auditability and Safety (FEAS) and discuss if and how these support the required qualities. Moreover, trust can be impacted throughout the life cycle of AI-based systems, and we therefore introduce the concept of Chain of Trust to discuss trustworthiness technologies in all stages of the life cycle. In so doing we establish the ways in which machine learning technologies support trusted AI-based systems. Finally, FEAS has obvious relations with known frameworks and therefore we relate FEAS to a variety of international 'principled AI' policy and technology frameworks that have emerged in recent years.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Current academic and public discourses are predominantly structured around the guiding principles towards trustworthy AI [62, 64]”
From Designing for Responsible Trust in AI Systems: A Communication Perspective (2022) · cites this paper as [62]
In the citing paper
“These earlier models have later been adapted to the context of human-technology, human-automation, and human-AI relations (Toreini et al., 2020;Siau & Wang, 2018;Hoff & Bashir, 2015;Schaefer et al., 2016;Riegelsberger et al., 2005;Kaplan et al., 2023;R. Yang & Wibowo, 2022).”
From Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation (2025) · cites this paper as Toreini et al., 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 1×
“, [75, 80] and the unified framework for local explainers which generalises these and other existing methods [64]), global explainers (e.”
BackgroundLearning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“Supervised Learning algorithms are mainly used in object recognition [54], machine translation [83], filtering spams [32], etc.”
Method"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Jain, A. K., Murty, M. N., & Flynn, P. J. (1999) · ACM Computing Surveys · doi:10.1145/331499.331504 · Cited by 13,199 · cited 1×
“that takes xas input and detects a hidden pattern representation as output, y. The problems that unsupervised learning tackles include grouped a dataset based on a similarity metric (a.k.a clustering [48]), projecting data to a reduced dimension space (e.g. PCA methods [53]) and pre{training algorithms for the other t…”
MethodGauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736 · cited 5×
“While each of the attributes are related and may reinforce one another they are also separable [67].”
BackgroundMethodInfluentialIntriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143 · cited 1×
“These meth-ods deal only with data, but it is also relevant to consider integrity during the execution of the algorithm, e.g., in the training stage [26, 13, 11, 61, 85].”
BackgroundDeep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578 · cited 1×
“Careless preparation of the stored data would leak information to an attacker [61] but confidentiality can be enhanced in many ways, for instance through approaches for differential privacy [1, 34], homomorphic encryption [47] or cryptography integrated in machine learning algorithms [79].”
Background
Research works printed but not linked: 11
- [6] Susan Athey and Guido W Imbens. Machine learning methods for estimating heterogeneous causal effects. stat , 1050(5):1-26, 2015. -
- [9] Robert Bartlett, Adair Morse, Richard Stanton, and Nancy Wallace. Consumer-Lending Discrimination in the Era of FinTech. Unpublished working paper. University of California, Berkeley , 2018. -
- [34] Cynthia Dwork. Differential privacy. Encyclopedia of Cryptography and Security , pages 338-340, 2011. -
- [36] Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. Why does unsupervised pretraining help deep learning? Journal of Machine Learning Research , 11(Feb):625-660, 2010. -
- [38] Jessica Fjeld, Hannah Hilligoss, Nele Achten, Maia Levy Daniel, Sally Kagay, and Joshua Feldman. Principled Artificial Intelligence: Mapping Consensus and Divergence in Ethical and Rights-Based Approaches. 2019. -
- [41] Carlos Adriano Gon¸ calves, Celia Talma Gon¸ calves, Rui Camacho, and Eugenio C Oliveira. The impact of Pre-Processing on the Classification of MEDLINE Documents. Pattern Recognition in Information Systems, Proceedings of the 10th International Workshop on Pattern Recognition in Information Systems, PRIS 2010, In conjunction with ICEIS 2010 , page 10, 2010. -
- [54] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems , pages 1097-1105, 2012. -
- [60] Zachary C Lipton. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 , 2016. - · arXiv
- [68] Donald Michie, David J Spiegelhalter, C C Taylor, and others. Machine learning. Neural and Statistical Classification , 13, 1994. -
- [70] Arvind Narayanan. Translation tutorial: 21 fairness definitions and their politics. In Proc. Conf. Fairness Accountability Transp., New York, USA , 2018. -
- [92] Brian Wynne. A reflexive view of the expert-lay knowledge divide. Risk, environment and modernity: Towards a new ecology , 40:44, 1996. -
Cited by
Items 101–200 of 373
Rethinking Transparency as a Communicative Constellation
Eyert, F., & Lopez, P. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594010 · Cited by 36
“The FAccT literature has suggested that information and explanations can play a role in strengthening overall trust in algorithmic systems: If a user knows more about what a machine does then her interaction with it will be infused by trust [58, 68, 82].”
BackgroundA federated and explainable approach for insider threat detection in IoT
Amiri-Zarandi, M., Karimipour, H., & Dara, R. A. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100965 · Cited by 33
User Perceptions of News Recommender Systems and Trust in Media Outlets: A Five-Country Study
Blassnig, S., Mitova, E., Strikovic, E., Urman, A., de Vreese, C. H., Hannák, A., & Esser, F. (2024) · Journalism Studies · doi:10.1080/1461670x.2024.2364628 · Cited by 29
“Users ’ algorithmic appreciation and trust in AI have also been studied in computer science (e.g., Logg, Minson, and Moore 2019; Toreini et al. 2020).”
Building Trust in Artificial Intelligence: A Systematic Review through the Lens of Trust Theory
Regona, M., Yiğitcanlar, T., Hon, C. K. H., & Teo, M. M. (2026) · ACM Computing Surveys · doi:10.1145/3789256 · Cited by 33
Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical ContextPreprint
Toreini, E., Aitken, M., Coopamootoo, K., Elliott, K., González-Zelaya, V., Missier, P., Ng, M., & van Moorsel, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08911 · Cited by 33
“We refer to [214] for a detailed discussion of various additional characteristics of the chain of trust.”
BackgroundMethodResultInfluentialSelf-citationTrustworthy AI-based Performance Diagnosis Systems for Cloud Applications: A Review
Xin, R., Wang, J., Chen, P., & Zhao, Z. (2025) · ACM Computing Surveys · doi:10.1145/3701740 · Cited by 30
“Toreini et al. [189] present four trustworthy ML technologies regarding fairness, explainability, audibility, and safety to support the development of trusted AI-based systems.”
The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results
Fomicheva, M., Lertvittayakumjorn, P., Zhao, W., Eger, S., & Gao, Y. (2021) · Workshop on Evaluation and Comparison of NLP Systems (Eval4NLP) · doi:10.18653/v1/2021.eval4nlp-1.17 · Cited by 46
To Trust or Distrust AI: A Questionnaire Validation Study
Scharowski, N., Perrig, S. A. C., von Felten, N., Aeschbach, L. F., Opwis, K., Wintersberger, P., & Brühlmann, F. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732025 · Cited by 37
“There are several definitions [3, 94, 95] and models [e.g., 15, 29, 48, 53, 61, 63, 93] of trust in AI currently in circulation.”
Mehdiyev, N., Houy, C., Gutermuth, O., Mayer, L., & Fettke, P. (2021) · Lecture notes in information systems and organisation · doi:10.1007/978-3-030-86790-4_28 · Cited by 35
“Another study suggests that various categories of trustworthiness approaches for AI such as fairness, explainability, auditability and safety should be considered when designing and implementing AI-based solutions [21].”
BackgroundLassiter, T. B., & Fleischmann, K. R. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3686963 · Cited by 26
“The definitions of trust across different disciplines vary considerably [28].”
(Re)Conceptualizing trustworthy AI: A foundation for change
Wirz, C. D., Demuth, J. L., Bostrom, A., Cains, M. G., Ebert‐Uphoff, I., Gagne, D. J., Schumacher, A., McGovern, A., & Madlambayan, D. (2025) · Artificial Intelligence · doi:10.1016/j.artint.2025.104309 · Cited by 31
Trust in AI and Implications for AEC Research: A Literature Analysis
Emaminejad, N., North, A. M., & Akhavian, R. (2022) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784483893.037 · Cited by 31
Trustworthy AI and the Logics of Intersectional Resistance
Knowles, B., Fledderjohann, J., Richards, J. T., & Varshney, K. R. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3593986 · Cited by 30
“Is it not possible that one person’s distrust of AI is as “justified” [96] as another person’s trust of the same AI, meaning that trustworthiness is at least partially subjective?”
BackgroundA step toward building a unified framework for managing AI bias
Rana, S. A., Azizul, Z. H., & Awan, A. A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1630 · Cited by 23
“Explainable AI techniques, such as providing interpretable explanations for decisions, can also enhance fairness and accountability ( Toreini et al., 2020 ).”
BackgroundOut-of-Distribution Detection Algorithms for Robust Insect Classification
Saadati, M., Balu, A., Chiranjeevi, S., Jubery, T. Z., Singh, A. K., Sarkar, S., Singh, A., & Ganapathysubramanian, B. (2024) · Plant Phenomics · doi:10.34133/plantphenomics.0170 · Cited by 25
To Err Is AI! Debugging as an Intervention to Facilitate Appropriate Reliance on AI Systems
He, G., Bharos, A., & Gadiraju, U. (2024) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/3648188.3675130 · Cited by 24
“To help users assess the trustworthiness of AI systems, a practical solution that has been proposed, is to provide meaningful explanations along with AI advice [50, 56].”
Interrogating AI: Characterizing Emergent Playful Interactions with ChatGPT
Nikghalb, M. R., & Cheng, J. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711015 · Cited by 27
“For example, Toreini et al. [44] proposed a framework that captured four key characteristics of trustworthy technologies: fairness, explainability, auditability, and safety.”
Mohammed, K. O., & Shehu, A. (2023) · Open Journal of Physical Science · doi:10.52417/ojps.v4i1.458 · Cited by 34
“It is necessary to mitigate the bias and unfairness in data for ethical reasons and to gain users’ trust in AI systems (Toreini et al. , 2020 (Zhang & Lu, 2021; Ghassemi et al. , 2021; Alikhademi et al. , 2021).”
BackgroundDesigning and Evaluating User Experience of an AI-Based Defense System
Park, S., Kim, H. K., Park, J., & Lee, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3329257 · Cited by 25
Naik, D. S. B., & Dondeti, V. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-024-01835-3 · Cited by 22
A survey of controllable learning: methods and applications in information retrieval
Shen, C., Zhang, X., Shi, T., Zhang, C., Xie, G., Xu, J., He, M., & Fan, J. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-025-41366-5 · Cited by 27
“Trustworthiness in machine learning is becoming increasingly important, with considerations such as controllability, fairness, privacy, and interpretability gaining prominence [57–60].”
Fifty Shades of Grey: In Praise of a Nuanced Approach Towards Trustworthy Design
Thornton, L., Knowles, B., & Blair, G. S. (2021) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3442188.3445871 · Cited by 26
“Whilst being theorised in a myriad of different ways, one element that is common to studies of trust is an emphasis on evidence of trustworthiness [22, 28, 29, 84, 91, 94, 102, 104, 107, 133, 142].”
BackgroundFraud Detection in Fintech Leveraging Machine Learning and Behavioral AnalyticsPreprint
Josyula, H. P. (2023) · Research Square · doi:10.21203/rs.3.rs-3548343/v1 · Cited by 22
Robertson, S., & Díaz, M. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3534638 · Cited by 31
Kundu, R. K., Elsaid, O. Y., Calyam, P. P., & Hoque, K. A. (2023) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3581641.3584044 · Cited by 26
Busch, P. A. (2023) · Government Information Quarterly · doi:10.1016/j.giq.2023.101872 · Cited by 24
Sei, Y., Onesimu, J. A., & Ohsuga, A. (2022) · IEEE Access · doi:10.1109/access.2022.3208715 · Cited by 21
“However, we need to consider privacy and fairness when creating such machine learning models [3], [4].”
BackgroundMitigating Algorithm Aversion in Recruiting: A Study on Explainable AI for Conversational Agents
Fleiß, J., Bäck, E., & Thalmann, S. (2024) · ACM SIGMIS Database the DATABASE for Advances in Information Systems · doi:10.1145/3645057.3645062 · Cited by 25
“From the technical perspective, XAI has been introduced as a solution to the black box problem; it was found to increase the acceptance of AI (El Bekri et al., 2020; Toreini et al., 2020).”
BackgroundSchmitz, A., Akila, M., Hecker, D., Poretschkin, M., & Wrobel, S. (2022) · at - Automatisierungstechnik · doi:10.1515/auto-2022-0012 · Cited by 26
“tensive research for several years [16], [17], [54].”
BackgroundToward a taxonomy of trust for probabilistic machine learning
Broderick, T., Gelman, A., Meager, R., Smith, A. L., & Zheng, T. (2023) · Science Advances · doi:10.1126/sciadv.abn3999 · Cited by 25
“We point the interested reader to resources on human trust in artificial intelligence (AI) (9, 10), trust in computing (11), and trust more generally (12).”
BackgroundScriven, A., Kedziora, D. J., Musiał, K., & Gabryś, B. (2023) · Foundations and Trends® in Information Systems · doi:10.1561/2900000030 · Cited by 23
Visualization for Trust in Machine Learning Revisited: The State of the Field in 2023
Chatzimparmpas, A., Kucher, K., & Kerren, A. (2024) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2024.3360881 · Cited by 19
Nittas, V., Daniore, P., Landers, C., Gille, F., Amann, J., Hubbs, S., Puhan, M. A., Vayena, E., & Blasimme, A. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000189 · Cited by 20
Trust Dynamics in AI-Assisted Development: Definitions, Factors, and Implications
Sabouri, S., Eibl, P., Zhou, X., Ziyadi, M., Medvidović, N., Lindemann, L., & Chattopadhyay, S. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00199 · Cited by 33
“TAI [67]–[69], HAI [70], MedAI [71] ✓ Comprehensibility was crucial among developers, similar to how trust is tied to explainability, transparency, and interpretability in AI systems.”
Cai, J., Fu, X., Gu, Z., & Wu, R. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2212224 · Cited by 20
“It plays a key role in human acceptance and use of AI services and products (Toreini et al., 2020).”
The Role of Uncertainty Quantification for Trustworthy AI
Deuschel, J., Foltyn, A., Roscher, K., & Scheele, S. (2024) · Springer eBooks · doi:10.1007/978-3-031-64832-8_5 · Cited by 28
Liu, J., Wang, Z., Xie, J., & Pei, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.18518 · Cited by 18
Kelly, S., Kaye, S.-A., White, K. M., & Oviedo-Trespalacios, O. (2025) · AI & SOCIETY · doi:10.1007/s00146-025-02334-6 · Cited by 17
“To build AI-based systems that users can trust, the trust-worthiness of AI systems must be understood (Toreini et al. 2020).”
Artificial intelligence in nephrology: predicting CKD progression and personalizing treatment
Yuan, S., Guo, L., & Xu, F. (2025) · International Urology and Nephrology · doi:10.1007/s11255-025-04878-4 · Cited by 20
“Table 3 goes into further detail about these tactics for building trust and resolving ethical issues [422–425].”
Li, F., Zhu, Q., Yuan, K., Ji, F., Paul, A., Lee, P., Radeloff, V. C., & Chen, M. (2024) · Earth s Future · doi:10.1029/2024ef004588 · Cited by 19
“Finally, while the concept of trustworthiness can be varied in different disciplines (Toreini et al., 2020), trustworthy ML in computer science includes other critical aspects apart from interpretability and accuracy, such as fairness, auditability, privacy, and safety (Eshete, 2021; Murdoch et…”
Selective Forgetting in Machine Learning and Beyond: A Survey
Sha, A. S., Nunes, B. P., & Haller, A. (2026) · ACM Computing Surveys · doi:10.1145/3796542 · Cited by 18
“Originally, machine unlearning aimed to enhance privacy by erasing traces of training data, reducing the risk of privacy leaks.”
Disparate Impact Diminishes Consumer Trust Even for Advantaged Users
Draws, T., Szlávik, Z., Timmermans, B., Tintarev, N., Varshney, K. R., & Hind, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-79460-6_11 · Cited by 18
“It has been argued that fairness plays a key role in fostering trust in AI [4,34,37,39,40].”
BackgroundProblem Understanding of Fake News Detection from a Data Mining Perspective
Chua, H. N., Khan, Q., Jasser, M. B., & Wong, R. T. K. (2023) · IEEE International Conference on Control System, Computing and Engineering · doi:10.1109/iccsce58721.2023.10237152 · Cited by 18
“3) Interpretability of ML algorithms: The study of effective human-computer interaction approaches to inform ML algorithms' decision-making logic can improve transparency and perceived fairness and increase user trust [24].”
BackgroundSingh, R., Mayank Vatsa, A., & Ratha, N. (2020) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/3430984.3431966 · Cited by 16
“(1) How to automatically measure/evaluate trustworthiness and decency of an AI system? (2) How to integrate trustworthiness and decency with the performance/accuracy of the system? (3) How to analyze the relationship between decency and different factors of trustworthy and dependable AI [44]? (4) How to democratize tr…”
The Alchemy of Trust: The Creative Act of Designing Trustworthy Socio-Technical Systems
Thornton, L., Knowles, B., & Blair, G. S. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533196 · Cited by 20
“…widely used [71, 82], including: the addition of predictability [26, 43] and of transparency and identification [93]; and has been applied to: AI [115], online recommendation agents [9], computer-mediated communication [36, 97–99], digital information [56], and to model trust in technology based…”
Toreini, E., Mehrnezhad, M., & van Moorsel, A. (2023) · International Journal of Information Security · doi:10.1007/s10207-023-00774-z · Cited by 19
“Demonstrating the fairness of algorithms is critical to the continued proliferation and acceptance (and trustworthiness) of algorithmic decision-making in general [32] and AI-based systems in particular [48].”
Self-citationNuh, A., Rizan, M., & Sadat, A. M. (2025) · Interdisciplinary Journal of Information Knowledge and Management · doi:10.28945/5444 · Cited by 17
“Trust in the platform can lead to increased customer satisfaction (Chen et al., 2022; Toreini et al., 2019).”
Ali, O., Murray, P., Al‐Ahmad, A., Jeon, I., & Dwivedi, Y. K. (2025) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2025.100762 · Cited by 15
Sample-Specific Output Constraints for Neural Networks
Brosowsky, M., Keck, F., Dünkel, O., & Zöllner, M. J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16841 · Cited by 15
de Bie, K., Lučić, A., & Haned, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06982 · Cited by 15
“Similarly, Toreini et al. (2020) relate trust in AI to the belief that an AI system will behave in a way that is generally beneficial to the trustor, which they relate to larger issues of justice and fairness (e.g. does this system discriminate against me?).”
BackgroundVining, R., Karimian, S., McDonald, N., Ebiele, M., Doyle, B., McKenna, L., Ward, M. E., Bendechache, M., & Brennan, R. (2025) · Ergonomics · doi:10.1080/00140139.2025.2512426 · Cited by 15
“This assumption needs to be challenged, and the link between trustworthiness, trust and outcomes needs to be verified (Toreini et al. 2020; Mccradden et al. 2023; Ulfert et al. 2024; Ahmed et al. 2023).”
A Study on the Modeling of Major Factors for the Principles of AI Ethics
Lim, J. H., & Kwon, H.-Y. (2021) · Annual International Conference on Digital Government Research · doi:10.1145/3463677.3463733 · Cited by 16
“"Transparency" emphasizes that decisions made by AI appear visible, understandable, and transparent to both developers and users [33].”
BackgroundDeep learning-based cell segmentation for rapid optical cytopathology of thyroid cancer
Jermain, P. R., Oswald, M., Langdun, T., Wright, S., Khan, A. A., Stadelmann, T., Abdulkadir, A., & Yaroslavsky, A. N. (2024) · Scientific Reports · doi:10.1038/s41598-024-64855-2 · Cited by 13
“In general, AI systems are not considered trustworthy for autonomous medical applications 49 .”
How Can I Signal You To Trust Me: Investigating AI Trust Signalling in Clinical Self-Assessments
Kollerup, N. K., Wester, J., Skov, M. B., & van Berkel, N. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3661612 · Cited by 16
“For example, Hauptman et al. recently explored the use of ABI in designing and implementing trustworthy AI systems [63].”
BackgroundOn the Explanation of AI-Based Student Success Prediction
Afrin, F., Hamilton, M., & Thevathyan, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-08754-7_34 · Cited by 16
“Therefore, the AI systems need to be transparent and the users must understand the extent to which they can trust the outcomes of the underlying machine learning technologies [12].”
BackgroundTowards explainable metaheuristic: mining surrogate fitness models for importance of variables
Singh, M., Brownlee, A. E. I., & Cairns, D. R. (2022) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3520304.3533966 · Cited by 20
“day-to-day life has brought with it ethics concerns[42], and a lack of trust from those users directly impacted by the automated decision making [2, 38].”
BackgroundMachine assistance for credit approval? Random wheel can recommend and explain
Khan, A., & Ghosh, S. K. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119231 · Cited by 13
Towards Defining a Trustworthy Artificial Intelligence System Development Maturity Model
Das, S. D., Bala, P. K., & Mishra, A. N. (2023) · Journal of Computer Information Systems · doi:10.1080/08874417.2023.2251443 · Cited by 17
“50 This concept serves as the foundation for the literature review and interactions with the specialists.”
Keeping it Human: A Focus Group Study of Public Attitudes Towards AI in Banking
Aitken, M., Ng, M., Toreini, E., van Moorsel, A., Coopamootoo, K., & Elliott, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-66504-3_2 · Cited by 15
“While, there is substantial interest in ethical practice relating to AI and growing consideration of what it means for AI to be trustworthy (3,4), as well as some evidence of growing interest in what this means in the financial sector 1 .”
BackgroundSelf-citationA Neural Model to Jointly Predict and Explain Truthfulness of Statements
Brand, E., Roitero, K., Soprano, M., Rahimi, A., & Demartini, G. (2022) · Journal of Data and Information Quality · doi:10.1145/3546917 · Cited by 16
“Without providing users with an explanation, the decision provided by an automated system is far less likely to be trusted [35], especially as it is not generated by humans.”
BackgroundA Survey on Data-driven COVID-19 and Future Pandemic Management
Tao, Y., Yang, C., Wang, T., Coltey, E., Jin, Y., Liu, Y., Jiang, R., Fan, Z., Song, X., Shibasaki, R., et al. (2022) · ACM Computing Surveys · doi:10.1145/3542818 · Cited by 17
“The phylogenetic tree view has been employed by References [104, 105] to track the circulating lineages of COVID-19 and elucidate the relationships among the variants and the evolution over”
BackgroundInfluentialJo, J., Zhang, H., Cai, J., & Goyal, N. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732077 · Cited by 17
“This insight aligns with a dualistic perspective on trust [66], which considers trust in both the technology and its developers [49, 68].”
The Reel Deal: Designing and Evaluating LLM-Generated Short-Form Educational Videos
Stavrinou, L., Constantinides, A., Belk, M., Vassiliou, V., Liarokapis, F., & Constantinides, M. (2025) · International Conference of the ACM Greek SIGCHI Chapter (CHIGreece) · doi:10.1145/3749012.3749048 · Cited by 14
“Furthermore, learners’ attitudes toward AI-generated educational content are not solely shaped by its utility, but also by perceived trustworthiness [15, 39, 48, 50].”
Seo, H., Lee, S., Lee, D., & Xiong, A. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31397 · Cited by 13
“Machine learning researchers also pay attention to the importance of trust which is linked to justification issues of models (Ribeiro, Singh, and Guestrin 2016; Lipton 2018; Toreini et al. 2020).”
BackgroundTaking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence
Crum, C. R., & Coglianese, C. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651170 · Cited by 15
“Auditing models for larger concepts like “trustworthiness” has been developed through trust scores [25], [26], Trust Matrices and Densities [27], and Chain of Trust [28].”
BackgroundAccountable AI for Healthcare IoT Systems
Bagave, P., Westberg, M., Dobbe, R., Janssen, M., & Ding, A. Y. (2022) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa56441.2022.00013 · Cited by 16
Fiduciary Responsibility: Facilitating Public Trust in Automated Decision Making
Harper, S. B., & Weber, E. (2022) · Journal of Social Computing · doi:10.23919/jsc.2022.0017 · Cited by 11
Meta-Trend of Trust Factors in Autonomous Vehicles
Vongvit, R., Lee, J., Itoh, M., & Lee, S. C. (2022) · International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI) · doi:10.1145/3544999.3552528 · Cited by 12
Informed Deep Learning for Anomaly Detection in Cyber-Physical Systems
Cobilean, V., Mavikumbure, H. S., Wickramasinghe, C. S., Marino, D., & Manic, M. (2023) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit58465.2023.10143126 · Cited by 10
“A safe artificial intelligence system should not only produce accurate predictions on known context but also detect unknown examples and reject them (or hand them over to human users for safe handling) [6].”
BackgroundFairness, explainability, privacy, and robustness for trustworthy algorithmic decision-making
Majumdar, S. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-85713-0.00017-7 · Cited by 10
Aspects and Views on Responsible Artificial Intelligence
Brumen, B., Göllner, S., & Tropmann-Frick, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25599-1_29 · Cited by 10
Reducing organizational inequalities associated with algorithmic controls
Li, Y., & Xiang, B. (2024) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00137-0 · Cited by 11
“Research on trustworthy AI has emerged in the past few years, which generally examines AI accountability, transparency, explainability, interpretability, fairness, safety, privacy, and security [19, 20, 22, 23, 110–113].”
InfluentialZhu, Y., Hua, G., Liu, X., Wang, C., & Tang, M. (2025) · Frontiers in Psychology · doi:10.3389/fpsyg.2025.1539054 · Cited by 14
“Beyond performance, ensuring fairness, interpretability, auditability, and security is crucial for fostering trust (Toreini et al., 2020).”
Ta, N., Zeng, J., & Li, Z. (2025) · Information Communication & Society · doi:10.1080/1369118x.2025.2537803 · Cited by 10
“Inconsistencies across languages and demographics may erode user trust (Toreini et al., 2020) and hinder AI development.”
Exploring Counterfactual Explanations for Predicting Student Success
Afrin, F., Hamilton, M., & Thevathyan, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36021-3_44 · Cited by 9
“Additionally, improved explainability can help build trust in the use of ML by ensuring that stakeholders understand the basis for the predictions being made [7].”
AI-based Market Intelligence Systems for Farmer Collectives: A Case Study from India
Ladhar, R., Sharma, S., Tangirala, S., Gupta, N., Azeem, A., Jain, A., Katakam, B. C., Bommakanti, A., Sankaraiah, C., Piridi, H. P., et al. (2023) · ACM Journal on Computing and Sustainable Societies · doi:10.1145/3609262 · Cited by 9
“Factors such as fairness, explainability, auditability, and safety have been identiied as crucial to build a trustworthy relationship, and to reinforce these throughout the lifecycle of a project from its design to development and deployment [39].”
BackgroundVerifiable Fairness: Privacy–preserving Computation of Fairness for Machine Learning Systems
Toreini, E., Mehrnezhad, M., & van Moorsel, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-54129-2_34 · Cited by 12
Self-citationMitigative Strategies for Recovering From Large Language Model Trust Violations
Martell, M. J., Baweja, J. A., & Dreslin, B. D. (2024) · Journal of Cognitive Engineering and Decision Making · doi:10.1177/15553434241303577 · Cited by 14
“Appropriate trust is driven by four primary characteristics that comprise the ability, benevolence, integrity, and predictability (ABI+) framework (Dietz & Den Hartog, 2006; Mayer et al., 1995; Toreini et al., 2020).”
GAOR: Genetic Algorithm-Based Optimization for Machine Learning Robustness in Communication Networks
Thompson, A. F.-B., & Suomalainen, J. (2025) · Network · doi:10.3390/network5010006 · Cited by 10
A Framework for Trustworthy AI in Credit Risk Management: Perspectives and Practices
Mazumder, S., Dhar, S., & Asthana, A. (2023) · Computer · doi:10.1109/mc.2023.3236564 · Cited by 12
“10,11,12,13 However, no formal definitions and classifications have been standardized so far.”
BackgroundTowards Uncertainty Aware Task Delegation and Human-AI Collaborative Decision-Making
Lee, M. H., & Tok, M. Z. Y. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732155 · Cited by 14
“To make AI more trustworthy [4, 24, 35, 53] and deployable in practice, researchers have proposed various design considerations and factors of trustworthy AI [24, 76, 80, 84].”
Rethinking AI inclusion: a systems thinking framework for policy, education, and participation
Sarkar, A. (2025) · AI and Ethics · doi:10.1007/s43681-025-00810-9 · Cited by 11
Trustworthy Sensor Fusion Against Inaudible Command Attacks in Advanced Driver-Assistance Systems
Guan, J., Pan, L., Wang, C., Yu, S., Gao, L., & Zheng, X. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3275931 · Cited by 12
Historical Perspectives on Service Design and Technology
Suoheimo, M., Trapani, P. M., & Miettinen, S. (2023) · Springer series in design and innovation · doi:10.1007/978-3-031-29306-1_3 · Cited by 8
Toward Patient-Centered AI Fact Labels: Leveraging Extrinsic Trust Cues
Yoo, D. W., Stroud, A. M., Zhu, X., Miller, J. E., & Barry, B. A. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735758 · Cited by 9
“For test sets, we provided performance data based on the evaluation results of similar technologies.”
On the Employment of Machine Learning in the Blockchain Selection Process
Scheid, E. J., Hy, R., Franco, M. F., Killer, C., & Stiller, B. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3212917 · Cited by 8
“Trust in ML and AI models is a widely researched and discussed topic in the literature; researchers have proposed using visualizations to foster trust in such a context [47] and identified the relation between trust in AI and trustworthy ML technologies [40].”
BackgroundMuhammad, J., Ghergherehchi, M., Ali, S., Song, H. S., & Rahim, N. (2026) · PLoS ONE · doi:10.1371/journal.pone.0342062 · Cited by 9
“There is a theoretical explanation for the variations in quality of life experienced by people with PD [17].”
Longo, L. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44070-0 · Cited by 7
Quyoum, A., & Wong, M. (2024) · Information Communication & Society · doi:10.1080/1369118x.2024.2331781 · Cited by 7
“For example, AI and trust often draw on the concept of explainability (Toreini et al., 2020) and communicating decisions and outcomes in an accessible way.”
Analysing the Predictability of Language Model Performance
Schellaert, W., Martínez‐Plumed, F., & Hernández‐Orallo, J. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3706118 · Cited by 19
“This approach aligns closely with the principles of trust and safety in AI [46], where ensuring the reliability of a model’s outputs is paramount [4].”
Humans or Machines for Teaching: Trust and Preferences among University Students
Asgari, M., Mannila, L., Tsai, F.-C., & Strömbäck, F. (2024) · International Conference on Education Technology and Computer · doi:10.1145/3702163.3702166 · Cited by 7
“One key factor for encouraging uptake as well as applying and us-ing AI-applications is trust (e.g., [9, 34, 39]), which can be nurtured through aspects such as transparency, explainability, accountability and fairness [32].”
The disagreement dilemma in explainable AI: can bias reduction bridge the gap
Bhardwaj, N., & Parashar, G. (2025) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-025-02712-9 · Cited by 8
“Additionally, investigating the intricate relationship between trust in AI and the development of trustworthy machine learning technologies reveals how user trust influences the widespread adoption of AI and the factors contributing to trustworthy AI systems (Toreini et al. 2020).”
Dong, Y., Wang, P., Geng, H., Liu, Y., & Wang, E. (2025) · Journal of X-Ray Science and Technology · doi:10.1177/08953996241304988 · Cited by 7
On Mismatched Detection and Safe, Trustworthy Machine Learning
Varshney, K. R. (2020) · Conference on Information Sciences and Systems · doi:10.1109/ciss48834.2020.1570627767 · Cited by 10
“…[8] competent use fair means to achieve its goals take responsibility for all its impact motivated to serve others’ interests as well as its own [9] ability integrity predictability benevolence [10] technicalcompe-tence reliability understandability distill these attributes into a set of…”
Reward innovation for long-term member satisfaction
Tang, G., Pan, J., Wang, H., & Basilico, J. (2023) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3604915.3608873 · Cited by 14
“Increasingly, recommendations are expected not only to be relevant but also of high quality [15], fair and trustworthy [40], and stakeholder-aware [27].”
Sen, P., Saha, S., Ganguly, D., Verma, M., & Roy, D. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557637 · Cited by 7
“transparency about how a model’s representation of data affects its decisions [1, 45, 49].”
BackgroundA Review on Human–Robot Trust in Home Service Robots
Balcha, H. B., Rauffet, P., Wegari, G. M., & Buche, C. (2025) · ACM Transactions on Human-Robot Interaction · doi:10.1145/3737893 · Cited by 10
“…and frameworks reviewed and presented in this paper, researchers can further advance the development of trustworthy and user-friendly home service robots, paving the way for enhanced collaboration between humans and robots and the seamless integration of these technologies into our daily lives.”
Trustworthy IoT Services With Blockchain and Information-Centric Networking: A Survey
Rafique, W., Qadir, J., & Erol‐Kantarci, M. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3631362 · Cited by 6
Newen, C., Müller, E., & Newen, A. (2025) · Topoi · doi:10.1007/s11245-025-10287-0 · Cited by 7
Analyzing Trustworthiness and Explainability in Artificial Intelligence: A Comprehensive Review
Dixit, M., Kansal, I., Khullar, V., Kumar, R., & Kumar, S. (2024) · Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) · doi:10.2174/0123520965308169240616144800 · Cited by 7
Metadata
- Authors
- Toreini, E., Aitken, M., Coopamootoo, K., Elliott, K., Zelaya, C. G., & van Moorsel, A.
- Affiliations
- Newcastle University (GB)
- Newcastle University, United Kingdom
- Venue
- Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2020-01-27
- Pages
- 272-283
- OpenAlex
- W2990399168
- Cited by
- 296
- References
- 89
- Citations by year
- 2026: 24 · 2025: 56 · 2024: 57 · 2023: 63 · 2022: 53 · 2021: 30 · 2020: 13
- FWCI
- 41.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Durham Research Online (Durham University) (submittedVersion, cc-by)
- University of Birmingham Research Portal (University of Birmingham) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Engineering and Physical Sciences Research Council (EP/R033595/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
- Keywords
- trust in AI, trustworthy machine learning, fairness, explainability, auditability, safety, trust chain, AI lifecycle
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.