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
- Susan Athey and Guido W Imbens . 2015. Machine learning methods for estimating heterogeneous causal effects. stat 1050, 5 ( 2015 ), 1--26. Susan Athey and Guido W Imbens. 2015. Machine learning methods for estimating heterogeneous causal effects. stat 1050, 5 (2015), 1--26.
- Robert Bartlett , Adair Morse , Richard Stanton , and Nancy Wallace . 2018. Consumer-Lending Discrimination in the Era of FinTech. Unpublished working paper . University of California , Berkeley ( 2018 ). Robert Bartlett, Adair Morse, Richard Stanton, and Nancy Wallace. 2018. Consumer-Lending Discrimination in the Era of FinTech. Unpublished working paper. University of California, Berkeley (2018).
- 10.5555/2040895.2040945 · doi:10.5555/2040895.2040945
- Cynthia Dwork . 2011. Differential privacy. Encyclopedia of Cryptography and Security ( 2011 ), 338--340. Cynthia Dwork. 2011. Differential privacy. Encyclopedia of Cryptography and Security (2011), 338--340.
- Carlos Adriano Gonçalves , Celia Talma Gonçalves , Rui Camacho , and Eugenio C Oliveira . 2010 . 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 (2010), 10. Carlos Adriano Gonçalves, Celia Talma Gonçalves, Rui Camacho, and Eugenio C Oliveira. 2010. 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 (2010), 10.
- Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105. Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.
- Zachary C Lipton . 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 ( 2016 ). Zachary C Lipton. 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016). · arXiv
- Donald Michie , David J Spiegelhalter , C C Taylor , and others. 1994. Machine learning. Neural and Statistical Classification 13 ( 1994 ). Donald Michie, David J Spiegelhalter, C C Taylor, and others. 1994. Machine learning. Neural and Statistical Classification 13 (1994).
- Arvind Narayanan . 2018 . Translation tutorial: 21 fairness definitions and their politics . In Proc. Conf. Fairness Accountability Transp. , New York, USA. Arvind Narayanan. 2018. Translation tutorial: 21 fairness definitions and their politics. In Proc. Conf. Fairness Accountability Transp., New York, USA.
- 10.5555/3305890.3306006 · doi:10.5555/3305890.3306006
- Brian Wynne . 1996. A reflexive view of the expert-lay knowledge divide. Risk, environment and modernity: Towards a new ecology 40 ( 1996 ), 44. Brian Wynne. 1996. A reflexive view of the expert-lay knowledge divide. Risk, environment and modernity: Towards a new ecology 40 (1996), 44.
Cited by
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612
Responsible Artificial Intelligence Governance: A Review and Research Framework
Papagiannidis, E., Mikalef, P., & Conboy, K. (2025) · The Journal of Strategic Information Systems · doi:10.1016/j.jsis.2024.101885 · Cited by 565
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Jacovi, A., Marasović, A., Miller, T., & Goldberg, Y. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445923 · Cited by 545
“on between any user and the AI [8, 11, 71, 76]. The recent rapid growth in the field ofexplainable AI (XAI) is also, in part, motivated by the need to maintain trust between the human user and the AI [31, 35, 46, 52, 59, 72]. By designing AI that users can and will trust to interact with, the AI can be safely implemen…”
BackgroundNazar, M., Alam, M. M., Yafi, E., & Su'ud, M. M. (2021) · IEEE Access · doi:10.1109/access.2021.3127881 · Cited by 312
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
Brundage, M., Avin, S., Wang, J., Belfield, H., Krueger, G., Hadfield, G., Khlaaf, H., Yang, J., Toner, H., Fong, R., et al. (2020) · arXiv · doi:10.48550/arxiv.2004.07213 · Cited by 306
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The relationship between trust in AI and trustworthy machine learning technologies. https://app.cochat.ai/papers/10.1145/3351095.3372834
- The paper
- Toreini, E., Aitken, M., Coopamootoo, K., Elliott, K., Zelaya, C. G., & van Moorsel, A. (2020). The relationship between trust in AI and trustworthy machine learning technologies. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. https://doi.org/10.1145/3351095.3372834
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.