Cited by 104Explainable Artificial Intelligence (XAI)Ethics and Social Impacts of AISoftware Testing and Debugging Techniques

The DOI matches its Crossref record; 103 of the 103 references it cites were found in a registry or an index.

Data-Centric Explanations: Explaining Training Data of Machine Learning Systems to Promote Transparency

Open access

Anik, Ariful Islam, Bunt, Andrea·2021·Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

DOI 10.1145/3411764.3445736

Open this paper in CoChat — free account Open PDF

Abstract

Training datasets fundamentally impact the performance of machine learning (ML) systems. Any biases introduced during training (implicit or explicit) are often reflected in the system's behaviors leading to questions about fairness and loss of trust in the system. Yet, information on training data is rarely communicated to stakeholders. In this work, we explore the concept of data-centric explanations for ML systems that describe the training data to end-users. Through a formative study, we investigate the potential utility of such an approach, including the information about training data that participants find most compelling. In a second study, we investigate reactions to our explanations across four different system scenarios. Our results suggest that data-centric explanations have the potential to impact how users judge the trustworthiness of a system and to assist users in assessing fairness. We discuss the implications of our findings for designing explanations to support users’ perceptions of ML systems.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Integrity signals

Registry

Crossref · 10.1145/3411764.3445736

Cites

103 of 103 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Generalized expectancies for internal versus external control of reinforcement.
Rotter, J. B. (1966) · Psychological Monographs: General and Applied · doi:10.1037/h0092976 · Cited by 21,937
"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
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Basics of Qualitative Research (3rd ed.): Techniques and Procedures for Developing Grounded Theory
Corbin, J., & Strauss, A. (2008) · SAGE · doi:10.4135/9781452230153 · Cited by 12,136
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
On the dimensionality of organizational justice: a construct validation of a measure.
Colquitt, J. (2001) · Journal of Applied Psychology · doi:10.1037/0021-9010.86.3.386 · Cited by 6,043
The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery.
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
Huang, G. B., Mattar, M., Berg, T. L., & Miller, E. G. (2008) · HAL · Cited by 4,445
The Black Box Society: The Secret Algorithms That Control Money and Information
Pasquale, F. (2015) · doi:10.4159/harvard.9780674736061 · Cited by 3,796
Untitled work
(2018) · Cited by 3,510

Show all 99 references

Research works printed but not linked: 9

Liliana Ardissono, Anna Goy, Giovanna Petrone, Marino Segnan, and Pietro Torasso. 2003. Intrigue: Personalized Recommendation of Tourist Attractions. Applied Artificial Intelligence: Special Issue on Artificial Intelligence for Cultural Heritage and Digital Libraries 17, 8–9: 687–714.
10.15779/Z38BG31 · DOI · Paper page
Zhengping Che, Sanjay Purushotham, Robinder Khemani, and Yan Liu. 2016. Interpretable Deep Models for ICU Outcome Prediction. AMIA ... Annual Symposium proceedings. AMIA Symposium 2016: 371–380.
10.18653/v1 · DOI
Sam Corbett-Davies, Emma Pierson, Avi Feller, and Sharad Goel. 2016. A computer program used for bail and sentencing decisions was labeled biased against blacks . It’ s actually not that clear. The Washington Post: 1–7.
Ben Green and Lily Hu. 2018. The Myth in the Methodology: Towards a Recontextualization of Fairness in Machine Learning. Proceedings of the machine learning: the debates workshop.
Lauren Kirchner, Surya Mattu, Jeff Larson, and Julia Angwin. 2016. Machine Bias. Propublica 23: 1–26. Retrieved from https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
Forough Poursabzi-Sangdeh, Daniel G. Goldstein, Jake M. Hofman, Jennifer Wortman Vaughan, and Hanna Wallach. 2018. Manipulating and Measuring Model Interpretability. Retrieved from http://arxiv.org/abs/1802.07810 · arXiv
10.18653/v1 · DOI

Sorted by citations

Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
Rong, Y., Leemann, T., Nguyen, T.-T., Fiedler, L., Qian, P., Unhelkar, V., Seidel, T., Kasneci, G., & Kasneci, E. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3331846 · Cited by 278
“Usability workload [3, 16, 21, 48, 66] helpfulness [13, 45, 46, 48, 56, 65, 67, 68] satisfaction [1, 6, 7, 16, 18, 19, 29, 47, 69, 70] undesired behavior detection [2, 24, 27, 38, 53, 57, 71, 72, 73, 74, 75, 76, 77, 78, 79] ease of use and others [1, 3, 13, 20, 21, 24, 30, 32, 37, 48, 65, 66, 71, 80, 81, 82, 83, 84, 8…”
BackgroundMethodInfluential
Towards a Science of Human-AI Decision Making: An Overview of Design Space in Empirical Human-Subject Studies
Lai, V., Chen, C., Smith-Renner, A., Liao, Q. V., & Tan, C. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594087 · Cited by 204
“Subjective metrics of understanding typically ask participants to directly rate their understanding of the AI [5, 12, 15, 18, 23, 75, 91, 105, 108], or some variations of it such as confidence in understanding [57], ease of understanding [46, 83], or confidence in simulation [2, 80].”
BackgroundInfluential
A literature review on applications of explainable artificial intelligence (XAI)
Kalasampath, K., Spoorthi, K. N., Sajeev, S., Kuppa, S. S., Ajay, K., & Maruthamuthu, A. (2025) · IEEE Access · doi:10.1109/access.2025.3546681 · Cited by 180
“[2], [3], [4], [5], [6], [7], [8].”
Generative AI for visualization: State of the art and future directions
Ye, Y., Hao, J., Hou, Y., Wang, Z., Xiao, S., Luo, Y., & Zeng, W. (2024) · Visual Informatics · doi:10.1016/j.visinf.2024.04.003 · Cited by 167
BreastScreening-AI: Evaluating medical intelligent agents for human-AI interactions
Calisto, F. M., Santiago, C., Nunes, N., & Nascimento, J. C. (2022) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2022.102285 · Cited by 125
Systematic review of data-centric approaches in artificial intelligence and machine learning
Singh, P. (2023) · Data Science and Management · doi:10.1016/j.dsm.2023.06.001 · Cited by 136
Improved Alzheimer’s Disease Detection by MRI Using Multimodal Machine Learning Algorithms
Battineni, G., Hossain, M. A., Chintalapudi, N., Traini, E., Dhulipalla, V. R., Mariappan, R., & Amenta, F. (2021) · Diagnostics · doi:10.3390/diagnostics11112103 · Cited by 93
“It is all about the data quality which helps to accurate data labelling [38].”
Background
A Survey of Data Quality Requirements That Matter in ML Development Pipelines
Priestley, M., O’donnell, F., & Simperl, E. (2023) · Journal of Data and Information Quality · doi:10.1145/3592616 · Cited by 86
“T r a n s p a r e n c y o f t h e m o d e l c a n b e s u pp o r t e d b y s e n s i t i v i t y t e s t i n g a n d e x p l a n a t i o n s [ 1 , 2 , 35 ] .”
BackgroundResult
Disentangling Fairness Perceptions in Algorithmic Decision-Making: the Effects of Explanations, Human Oversight, and Contestability
Yurrita, M., Draws, T., Balayn, A., Murray-Rust, D., Tintarev, N., & Bozzon, A. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581161 · Cited by 108
“For instance, previous studies have shown that data-centric explanations [7] have the potential to assist users in assessing fairness.”
Result
Rethinking open source generative AI: open washing and the EU AI Act
Liesenfeld, A., & Dingemanse, M. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3659005 · Cited by 123
“Practical approaches to implement such ideas typically revolve around the systematic collection and curation of data on various aspects of systems [2, 28, 46].”
Background
On Selective, Mutable and Dialogic XAI: a Review of What Users Say about Different Types of Interactive Explanations
Bertrand, A., Viard, T., Belloum, R., Eagan, J. R., & Maxwell, W. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581314 · Cited by 71
“Anik and Bunt [7] is an example of this interactivity type.”
BackgroundInfluential
Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation
Visser, R., Peters, T. M., Scharlau, I., & Hammer, B. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101357 · Cited by 58
“Anik and Bunt (2021), Liao and Varshney (2021), Mohseni et al. (2021) give an overview of different explanation approaches, or types, that are already used to answer such questions.”
Influential
Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work
Zheng, C., Wang, D., Wang, A. Y., & Ma, X. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517615 · Cited by 54
“The formative study has two parts: we first thoroughly surveyed relevant literature [5, 29, 31, 35, 37, 38, 42, 55] and industrial standard documentations [1, 2, 18, 36] to understand how a presentation deck looks like, and what contents are usually included.”
Background
Selective Explanations: Leveraging Human Input to Align Explainable AI
Lai, V. W.-M., Zhang, Y., Chen, C., Liao, Q. V., & Tan, C. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3610206 · Cited by 75
“…the effects of explanations on people’s task performance [6, 57, 108], efficiency [1, 17, 21, 34, 36, 39, 54, 55, 59, 64, 88, 99, 103], cognitive load [1, 37], understanding [4, 8, 11, 14, 21, 68, 88, 98, 103], subjective perceptions of AI [9, 15, 25, 37, 54, 55, 68, 75, 92] among others.”
Background
Mitigating Bias in Algorithmic Systems—A Fish-eye View
Orphanou, K., Otterbacher, J., Kleanthous, S., Batsuren, K., Giunchiglia, F., Bogina, V., Tal, A. S., Hartman, A., & Kuflik, T. (2022) · ACM Computing Surveys · doi:10.1145/3527152 · Cited by 58
“Explainability Management Domain Problem Solution Space Reference(s) ML Model Model Expainability Use of decision tree [38, 54, 75, 114, 178, 194, 231] Model Use of decision rules [45, 99, 129] Model Ontologies [19, 42, 167] Output Outcome Explainability Local explanations [168, 169, 201] Output/User Visualization met…”
Method
A Critical Survey on Fairness Benefits of Explainable AI
Deck, L., Schoeffer, J., De‐Arteaga, M., & Kühl, N. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658990 · Cited by 107
Explainable AI for government: Does the type of explanation matter to the accuracy, fairness, and trustworthiness of an algorithmic decision as perceived by those who are affected?
Aoki, N., Tatsumi, T., Naruse, G., & Maeda, K. (2024) · Government Information Quarterly · doi:10.1016/j.giq.2024.101965 · Cited by 75
A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities
Tocchetti, A., Corti, L., Balayn, A., Yurrita, M., Lippmann, P., Brambilla, M., & Yang, J. (2024) · ACM Computing Surveys · doi:10.1145/3665926 · Cited by 77
“Other works build tools, e.g., documentation or checklists, [7, 29, 74, 144] and workflows [205] to support making and documenting relevant choices when building or evaluating a model.”
An Overview of the Empirical Evaluation of Explainable AI (XAI): A Comprehensive Guideline for User-Centered Evaluation in XAI
Naveed, S., Stevens, G., & Robin-Kern, D. (2024) · Applied Sciences · doi:10.3390/app142311288 · Cited by 67
Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations
Bhattacharya, A., Ooge, J., Štiglic, G., & Verbert, K. (2023) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3581641.3584075 · Cited by 44
“ferent explanation methods, including data-centric approaches [3], feature importance [2], and example-based methods [2].”
BackgroundMethod
Effect of Explanation Conceptualisations on Trust in AI-assisted Credibility Assessment
Pareek, S., van Berkel, N., Velloso, E., & Goncalves, J. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3686922 · Cited by 42
Towards a multi-stakeholder value-based assessment framework for algorithmic systems
Yurrita, M., Murray-Rust, D., Balayn, A., & Bozzon, A. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533118 · Cited by 50
“3314243 [11] Ariful IslamAnik and Andrea Bunt.”
A Missing Piece in the Puzzle: Considering the Role of Task Complexity in Human-AI Decision Making
Salimzadeh, S., He, G., & Gadiraju, U. (2023) · Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization · doi:10.1145/3565472.3592959 · Cited by 42
“4% set up their studies in both conditions, either by changing the decision task [5] or artificially modifying the scenario.”
Background
Facets of algorithmic literacy: Information, experience, and individual factors predict attitudes toward algorithmic systems
Silva, D. E., Chen, C., & Zhu, Y. (2022) · New Media & Society · doi:10.1177/14614448221098042 · Cited by 46
“…to find methods that increase the transparency of algorithmic systems in the hopes of increasing understanding (Liao et al., 2020; Polack, 2020), improving product design (Eiband et al., 2018; Kizilcec, 2016), and improving attitudes toward those systems (Anik and Bunt, 2021; Eslami et al., 2019).”
Method
The methodology of studying fairness perceptions in Artificial Intelligence: Contrasting CHI and FAccT
van Berkel, N., Sarsenbayeva, Z., & Gonçalves, J. (2022) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2022.102954 · Cited by 48
Dealing with Uncertainty: Understanding the Impact of Prognostic Versus Diagnostic Tasks on Trust and Reliance in Human-AI Decision Making
Salimzadeh, S., He, G., & Gadiraju, U. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641905 · Cited by 41
“For example, in high-stake scenarios such as in the medical [39, 61, 67, 97], legal [6, 81, 86, 131], and financial [27, 36, 43, 45, 46] domains, individuals tend to exhibit a preference for human decision-makers over AI systems.”
Background
Human-Algorithm Collaboration with Private Information: Naïve Advice-Weighting Behavior and Mitigation
Balakrishnan, M., Ferreira, K., & Tong, J. D. (2025) · Management Science · doi:10.1287/mnsc.2022.03850 · Cited by 45
Watch Out for Updates: Understanding the Effects of Model Explanation Updates in AI-Assisted Decision Making
Wang, X., & Yin, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581366 · Cited by 38
“To this end, one promising direction is to supplement explanations of AI models with explanations of the underlying data [4], which in e�ect may help people establish some “knowledge” or data-driven insights about the domain.”
Background
Is this AI trained on Credible Data? The Effects of Labeling Quality and Performance Bias on User Trust
Chen, C., & Sundar, S. S. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580805 · Cited by 41
“Aside from communicating training data demographics [2] and labelers’ racial backgrounds [9], designers can convey the extent to which the labels match the raw training data.”
BackgroundInfluential
EXMOS: Explanatory Model Steering through Multifaceted Explanations and Data Configurations
Bhattacharya, A., Stumpf, S., Gosak, L., Štiglic, G., & Verbert, K. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642106 · Cited by 47
“Explanation methods have been categorised as model-specific or model-agnostic based on the degree of specificity [2, 5].”
Influential
Out of Context: Investigating the Bias and Fairness Concerns of “Artificial Intelligence as a Service”
Lewicki, K., Lee, M. S. A., Cobbe, J., & Singh, J. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581463 · Cited by 30
“Indeed, such activities also presents an opportunity for the HCI community, leveraging and extending work on how to provide means and tooling for meaningful transparency to support accountability [11, 27, 46, 62, 107].”
Background
The Past, Present, and Prospective Future of XAI: A Comprehensive Review
Islam, M. U., Mottalib, M. M., Hassan, M., Alam, Z. I., Zobaed, S., & Rabby, M. F. (2022) · Studies in computational intelligence · doi:10.1007/978-3-030-96630-0_1 · Cited by 30
A domain-specific language for describing machine learning datasets
Giner-Miguelez, J., Gómez, A., & Cabot, J. (2023) · Journal of Computer Languages · doi:10.1016/j.cola.2023.101209 · Cited by 29
An Agile Software Development Life Cycle Model for Machine Learning Application Development
Ranawana, R., & Karunananda, A. S. (2021) · SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI) · doi:10.1109/slaai-icai54477.2021.9664736 · Cited by 27
Ground Truth Or Dare: Factors Affecting The Creation Of Medical Datasets For Training AI
Zając, H. D., Avlona, N.-R., Kensing, F., Andersen, T. O., & Shklovski, I. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604766 · Cited by 25
“This has implications for scholarly discussions that focus on developing documentation frameworks that support the responsible and informed use of complex datasets [2, 5, 20, 31, 44].”
Background
Interrogating the T in FAccT
Corbett, E., & Denton, E. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594104 · Cited by 32
“find quite a few studies that empirically examine how end-users understand and use existing transparency mechanisms [5, 27, 41, 65]”
How can Explainability Methods be Used to Support Bug Identification in Computer Vision Models?
Balayn, A., Rikalo, N., Lofi, C., Yang, J., & Bozzon, A. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517474 · Cited by 26
“We draw inspiration from works situated at the intersection of machine learning and HCI that investigate how machine learning or related tools (e.g. explainability, debugging user-interfaces, etc.) are used [35], or could be used [20], and how to design them [4, 52].”
Background
``It Is a Moving Process": Understanding the Evolution of Explainability Needs of Clinicians in Pulmonary Medicine
Corti, L., Oltmans, R., Jung, J., Balayn, A., Wijsenbeek, M. S., & Yang, J. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642551 · Cited by 27
The landscape of data and AI documentation approaches in the European policy context
Micheli, M., Hupont, I., Delipetrev, B., & Soler-Garrido, J. (2023) · Ethics and Information Technology · doi:10.1007/s10676-023-09725-7 · Cited by 23
“Initiatives for distinct data types include Natural Language Processing (NLP) (Bender & Friedman, 2018; Lhoest et al., 2021; McMillan-Major et al., 2021; Shimorina & Belz, 2021), population data (Anik & Bunt, 2021), or images datasets (Prabhu and Birhane, 2020).”
Background
Transparency-Check: An Instrument for the Study and Design of Transparency in AI-based Personalization Systems
Schelenz, L., Segal, A., Adelio, O., & Gal, K. (2023) · ACM Journal on Responsible Computing · doi:10.1145/3636508 · Cited by 24
“The results of the study on user perceptions in popular real-world AI-based systems that use personalization show the discontents of users in several areas of transparency along the IPO + user control model.”
Background
"If it is easy to understand then it will have value": Examining Perceptions of Explainable AI with Community Health Workers in Rural India
Okolo, C. T., Agarwal, D., Dell, N. L., & Vashistha, A. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637348 · Cited by 28
“…on interviewing users and practitioners (UX designers, data scientists, researchers, etc.) to understand gaps in existing XAI tools [33, 36, 56, 67], evaluating XAI methods with various stakeholders [5, 17, 22, 35, 38, 59, 110], and introducing participatory co-design of XAI systems [76, 127, 132].”
Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
Black, E., Naidu, R. C. A., Ghani, R., Rodolfa, K. T., Ho, D. E., & Heidari, H. (2023) · ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) · doi:10.1145/3617694.3623259 · Cited by 19
When to Explain? Exploring the Effects of Explanation Timing on User Perceptions and Trust in AI systems
Chen, C., Liao, M., & Sundar, S. S. (2024) · International Symposium on Trustworthy Autonomous Systems (TAS) · doi:10.1145/3686038.3686066 · Cited by 20
“…to lay users, researchers have adopted the documentation approach by detailing training data-related information before AI interaction, and it has demonstrated effectiveness in helping users identify bias in machine learning algorithms [3] and shaping appropriate expectations and trust in AI [10].”
Communicating and combating algorithmic bias: effects of data diversity, labeler diversity, performance bias, and user feedback on AI trust
Chen, C., & Sundar, S. S. (2024) · Human-Computer Interaction · doi:10.1080/07370024.2024.2392494 · Cited by 19
When in Doubt! Understanding the Role of Task Characteristics on Peer Decision-Making with AI Assistance
Salimzadeh, S., & Gadiraju, U. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3627043.3659567 · Cited by 14
“…increasing capabilities of AI systems to perform tasks with high accuracy have led to increasing interest in incorporating these systems into human decision-making processes across various fields, such as finance [24, 32, 42, 44], healthcare [37, 62, 65, 84], and the legal domain [6, 71, 76, 106].”
Background
Follow the Successful Herd: Towards Explanations for Improved Use and Mental Models of Natural Language Systems
Brachman, M., Pan, Q., Do, H. J., Dugan, C., Chaudhary, A., Johnson, J. M., Rai, P., Chakraborti, T., Gschwind, T., Laredo, J. A., et al. (2023) · Proceedings of the 28th International Conference on Intelligent User Interfaces · doi:10.1145/3581641.3584088 · Cited by 11
“However, much of the work in the design and evaluation of human-centric XAI focuses on decision-based systems, such as medical decision systems [56, 96, 120, 135], bail decision systems [4, 33, 77], and recommendation systems [62, 86, 93].”
Background
Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions
Bhattacharya, A. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3638177 · Cited by 14
“Moreover, recent works have emphasised the need for Data-Centric AI (DCAI) [32] approaches for model improvement by improving the quality of the training data for building more reliable and trustworthy prediction models [5].”
Towards Unlocking the Hidden Potentials of the Data-Centric AI Paradigm in the Modern Era
Majeed, A., & Hwang, S. O. (2024) · Applied System Innovation · doi:10.3390/asi7040054 · Cited by 10
Faulty or Ready? Handling Failures in Deep-Learning Computer Vision Models until Deployment: A Study of Practices, Challenges, and Needs
Balayn, A., Rikalo, N., Yang, J., & Bozzon, A. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581555 · Cited by 13
“…a tool suggesting a workfow and artifacts, etc. Previous works around software debugging and machine teaching provide hints for its design, highlighting the importance of structured steps [84, 89]; structured documentation [6, 18, 33, 43, 81]; or warnings against graphical user-interfaces [128].”
BackgroundMethod
XAI in Automated Fact-Checking? The Benefits Are Modest and There's No One-Explanation-Fits-All
Lim, G., & Perrault, S. T. (2023) · Australian Conference on Computer-Human Interaction (OzCHI) · doi:10.1145/3638380.3638388 · Cited by 9
“One aspect examines how people understand, interact with, accept, and trust XAI [8, 31, 75, 81], where we place our work.”
Background
An Explanatory Model Steering System for Collaboration between Domain Experts and AI
Bhattacharya, A., Stumpf, S., & Verbert, K. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3631700.3664886 · Cited by 8
The Influence of Curiosity Traits and On-Demand Explanations in AI-Assisted Decision-Making
Cau, F. M., & Spano, L. D. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712165 · Cited by 13
Representation Debiasing of Generated Data Involving Domain Experts
Bhattacharya, A., Stumpf, S., & Verbert, K. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3631700.3664910 · Cited by 9
Towards Effective Human Intervention in Algorithmic Decision-Making: Understanding the Effect of Decision-Makers' Configuration on Decision-Subjects' Fairness Perceptions
Yurrita, M., Verma, H., Balayn, A., Gadiraju, U., Pont, S. C., & Bozzon, A. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713145 · Cited by 11
“Even if the effect found by Anik and Bunt [5] referred to training data rather than input data, we hypothesize that the type of input data will affect decision-subjects’ perceptions.”
Influential
A Human-Centered Approach to Interpretable Machine Learning in Clinical Decision Support Systems
Nimbalkar, V., Chawla, L., Adnan, M. M., Bhansali, A., Gupta, M., & Kalra, R. (2025) · International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI) · doi:10.1109/icaiihi67124.2025.11403473 · Cited by 7
“The major weakness in most works is the compromise of model accuracy and interpretability which typically leaves the developers to choose between performance and transparency [12,19].”
"This means nothing to me": Building credibility in conversational systems
Candello, H. C. D. S. P., Soella, G. M., Sanctos, C. S., Grave, M., & de Brito-Filho, A. A. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3603759 · Cited by 7
“Between values that could a priori guide the realworld observation was fairness [2, 10, 12, 15, 16], explainability [10, 11], accountability [1, 9, 11, 16], and trust [2, 8, 9, 20, 25].”
Background
Towards a Non-Ideal Methodological Framework for Responsible ML
Mothilal, R. K., Guha, S., & Ahmed, S. I. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642501 · Cited by 14
“…at various phases of ML lifecyle for data collection and processing [32, 96, 140], disaggregated evaluation of models, explaining model outcomes [4, 33, 79], ethical risk assessment [115, 123], and accountability [109], etc. Researchers also develop frameworks to evaluate ethical or fairness…”
Background
POP: Mining POtential Performance of New Fashion Products via Webly Cross-modal Query Expansion
Joppi, C., Skenderi, G., & Cristani, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_3 · Cited by 7
Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems
Bhattacharya, A., Stumpf, S., Croon, R. D., & Verbert, K. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713497 · Cited by 16
Unlocking the Tacit Knowledge of Data Work in Machine Learning
Cha, I., Oh, J., Park, C. Y., Han, J., & Lee, H. (2023) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3544549.3585616 · Cited by 6
“On the other hand, much work in the field of HCI is bridging the gap between the technical aspect of building ML datasets and understanding the roles and influences of humans making ML data [3, 5, 28, 30, 32].”
Background
Data journeys: Explaining AI workflows through abstraction
Daga, E., & Groth, P. (2023) · Semantic Web · doi:10.3233/sw-233407 · Cited by 7
“While much of the XAI literature has focused on the need to explain the outcomes of machine learning and speciﬁcally deep learning models [9], a new line of work has begun to emphasise the need to explain how systems are built and trained [6,24,60].”
Exploring the impact of explainable AI and cognitive capabilities on users’ decisions
Cau, F. M., & Spano, L. D. (2025) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-025-09438-0 · Cited by 16
“Recent studies have proposed integrating actionable data-centric explanations (Anik and Bunt 2021; Liao and Varshney 2021; Yurrita et al. 2023; Esfahani et al. 2024b; Bhattacharya et al. 2025) alongside model-centric ones, offering potential beneﬁts for both AI experts and lay users by connecting…”
A new hybrid data and model-centric predictive approach dedicated to industrial pipe maintenance
Braydi, A., Fossat, P., Casaburo, A., Pernet, V., Zwick, C., Ardabilian, M., & Bareille, O. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110821 · Cited by 5
“However, there has been a recent shift in focus towards the data-centric approach (Zajam et al., 2019; Anik and Bunt, 2021).”
A Review of Data-Centric Artificial Intelligence (DCAI) and its Impact on manufacturing Industry: Challenges, Limitations, and Future Directions
Nieberl, M., Zeiser, A., & Timinger, H. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00018 · Cited by 5
“Conversely, revealing problems with the training data can negatively impact trust [28].”
Background
Identifying Algorithmic Decision Subjects' Needs for Meaningful Contestability
Yurrita, M., Verma, H., Balayn, A., Alfrink, K., Gadiraju, U., & Bozzon, A. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757415 · Cited by 11
“Limiting information to output explanations might, therefore, hinder decision subjects’ ability to question structural aspects (e.g., data sources [7]) of the decision-making process [41].”
Mapping the Smart City: Participatory approaches to XAI
Gupta, S. (2023) · Designing Interactive Systems Conference · doi:10.1145/3563703.3593063 · Cited by 4
“Several methods and tools, such as model [44] and data documentation [4, 7, 22, 29] frameworks, have been designed to explain AI to experts [17].”
Method
A Canary in the AI Coal Mine: American Jews May Be Disproportionately Harmed by Intellectual Property Dispossession in Large Language Model Training
Precel, H., McDonald, A., Hecht, B. J., & Vincent, N. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642749 · Cited by 7
“For instance, Anik et al. [6] investigate how explanations of training data in ML systems can increase trans-parency and influence trustworthiness of systems.”
Background
A Learning Approach for Increasing AI Literacy via XAI in Informal Settings
Sneirson, M., Chai, J., & Howley, I. K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-64299-9_29 · Cited by 4
Designing multi-model conversational AI financial systems: understanding sensitive values of women entrepreneurs in Brazil
Candello, H. C. D. S. P., Soella, G. M., & Nascimento, L. D. C. (2024) · ACM International Conference on Interactive Media Experiences · doi:10.1145/3672406.3672409 · Cited by 4
“In order to unveil values in real-world situations, for instance: fairness [3, 19, 22, 31, 38], explainability [1, 19, 20], accountability [2, 17, 20, 38], trust [3, 12, 17, 25, 45, 50], and privacy [30, 42, 43, 49].”
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 7
“Concurrently, the human-computer interaction (HCI) communities have extensively explored strategies to ensure AI model fairness, accountability, transparency, and trust [2, 6, 15, 17, 46].”
Elements that Influence Transparency in Artificial Intelligent Systems - A Survey
Muralidhar, D., Belloum, R., de Oliveira, K. M., & Ashok, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42280-5_21 · Cited by 6
Dissecting users' needs for search result explanations
Juneja, P., Zhang, W., Smith, A., Lamba, H., Tetreault, J., & Jaimes, A. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642059 · Cited by 14
Will Health Experts Adopt a Clinical Decision Support System for Game-Based Digital Biomarkers? Investigating the Impact of Different Explanations on Perceived Ease-of-Use, Perceived Usefulness, and Trust
Chen, Y., Verbert, K., Gerling, K., Abeele, M.-E. V., & Abeele, V. V. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712139 · Cited by 6
“In accordance with the data-centric approach [8], it furnishes details about the dataset and models used for training, along with model accuracy and basic demographic information such as age.”
Influential
When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Market Outcomes and Adoption
Erlei, A., Cau, F. M., Georgiev, R., Kumar, S. C., Bizer, K., & Gadiraju, U. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791420 · Cited by 7
“Furthermore, additional information may also fail to improve human reliance if they cannot interpret the signals correctly or experience information overload [112].”
Social Transparency in Network Monitoring and Security Systems
Soroko, D., Savino, G.-L., Gray, N., & Schöning, J. (2023) · International Conference on Mobile and Ubiquitous Multimedia (MUM) · doi:10.1145/3626705.3627773 · Cited by 3
Making Smart Cities Explainable: What XAI Can Learn from the “Ghost Map”
Gupta, S., & Loukissas, Y. A. (2023) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3544549.3585847 · Cited by 3
“Alongside the creation of model documentation frameworks, XAI researchers have also designed systems to specifically document data creation processes such as “Data-centric Explanations” [2], “Datasheets” [16], “Dataset Nutrition Labels” [23], and “Data Statements” [4].”
Method
Why is "Problems" Predictive of Positive Sentiment? A Case Study of Explaining Unintuitive Features in Sentiment Classification
Qu, J., Arguello, J., & Wang, Y. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658547 · Cited by 3
Supporting User Critiques of AI Systems via Training Dataset Explanations: Investigating Critique Properties and the Impact of Presentation Style
Anik, A. I., & Bunt, A. (2024) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl/hcc60511.2024.00024 · Cited by 4
“Information about the training data is a central component of training dataset explanations [19], where the primary goal is to increase system transparency by informing the user about the formation of training datasets and the training process.”
BackgroundMethodInfluentialSelf-citation
Generative AI for Visualization
Jhanjhi, N. Z., Shah, I. A., & Nawaz, S. (2024) · Advances in web technologies and engineering book series · doi:10.4018/979-8-3693-3703-5.ch003 · Cited by 3
Thinking Like a Scientist: Can Interactive Simulations Foster Critical AI Literacy?
Zhao, Y., Michal, A. L., Thain, N., & Subramonyam, H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98417-4_5 · Cited by 3
“Others have focused on understanding training data to explain how biases in training data can negatively affect the fairness of AI decisions (i.e., Explainable AI) [2].”
Prompt Coaching for Inclusiveness: A Media Literacy Approach to Increase Users’ Awareness of Algorithmic Bias and Prompting Efficacy
Chen, C., Liao, M., Phadnis, A. A., Li, Y., High, A. C., Abdullah, S., & Sundar, S. S. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791542 · Cited by 2
“In-formed by the documentation paradigm [41, 58], several studies have sought to disclose training data characteristics to help lay users recognize biases in machine learning models [3, 20, 21].”
HAEM: Obtaining Higher-Quality Classification Task Results with AI Workers
Yamashita, Y., Ito, H., Wakabayashi, K., Kobayashi, M., & Morishima, A. (2022) · ACM Web Science Conference (WebSci) · doi:10.1145/3501247.3531580 · Cited by 3
“For example, law [15, 19, 36], medicine [10, 32], finance [8, 20], education [3, 14], and leisure [29, 30].”
Background
Diversity Challenges in Recruiting for Human-Centered Explainable AI Studies
Anik, A. I., & Bunt, A. (2024) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl/hcc60511.2024.00067 · Cited by 2
“Our research specifically explores how to design AI explanations that communicate information about the training datasets used to train the systems [13], [14].”
BackgroundSelf-citation
AI Systems Quality: A Data-Centric Perspective
Belghiti, A. E., Sbaï, H., & Asri, H. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-95326-2_8 · Cited by 1
Filtering Instances and Rejecting Predictions to Obtain Reliable Models in Healthcare
Valeriano, M. G., Marzagão, D. K., Montelongo, A., Kiffer, C. R. V., Katz, N., & Lorena, A. C. (2026) · Machine Learning · doi:10.1007/s10994-025-06941-8 · Cited by 1
“Biases, inconsistencies, and a lack of standardization can severely compromise model performance and reliability [4].”
Designing Effective Training Dataset Explanations: The Impact of Information Depth and Progressive Disclosure
Anik, A. I., & Bunt, A. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742413.3789087 · Cited by 2
“Thisgapis especially relevant for Training dataset explanations [5, 6], which are typically longer than other types of AI explanations studied to date.”
InfluentialSelf-citation
How cultural cognition affects trust and perceived quality of AI explanations
Yuan, C. W., & Lee, Y.-H. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101021 · Cited by 2
Interacting with autonomous systems and intelligent algorithms – new theoretical considerations on the relation of understanding and trustPreprint
Krämer, N. C., Wischnewski, M., & Müller, E. (2023) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/h32ze · Cited by 2
Investigating Explanations that Target Training Data.
Anik, A. I., & Bunt, A. (2021) · IUI Workshops
Self-citation
Nailing Prediction: Experimental Evidence on the Value of Tools in Predictive Model DevelopmentPreprint
Yue, D., Hamilton, P., & Bojinov, I. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4300501
Data and databases in cardiovascular medicine and surgery
Shamavu, K. Y., & Tcheng, J. E. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-90534-3.00030-5
Desirability vs. feasibility: a research through design inquiry of explainable AI
Corti, L., & Yang, J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-340553-2.00010-1
Responsible Artificial Intelligence for Healthcare: Trends, Challenges, and Opportunities
Baker, S., & Ahn, E. (2025) · Springer eBooks · doi:10.1007/978-3-031-88024-7_1
Information Science Professional's Engagement in Developing Data Documentation Frameworks for Machine Learning
Huang, P., & Yang, Y. (2025) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.1443
“While data plays a crucial role in the development, evaluation, and deployment of machine learning (ML) models, it is also the key component in ensuring the fairness, transparency in the models (Anik & Bunt, 2021; Holstein et al., 2019).”
Understanding Human-AI Trust in the Context of Decision Making through the Lenses of Academia and Industry : Definitions, Factors, and Evaluation
Vereschak, O. (2022) · theses.fr (ABES) · doi:10.70675/7ecd53bfza7ccz4edfz8f1azdb8052ba1233
Misplaced trust in AI : the explanation paradox and the human-centric path. A characterisation of the cognitive challenges to appropriately trust algorithmic decisions and applications in the financial sector
Bertrand, A. (2024) · theses.fr (ABES) · doi:10.70675/216d3647z78bcz4c68z9ba9z2d0a029cf1b4 · Cited by 1
Sensemaking in Multi-Agent LLM Interfaces: How Users Interpret Transparency and Trustworthiness Cues
Pareek, S., Govers, J., Kollerup, N. K., Wong, E., Velloso, E., & Gonçalves, J. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791157 · Cited by 3
“…or reliable the AI is, through accuracy scores [32, 102, 104], confidence estimates [107], or uncertainty markers [7, 41, 81], while process transparency focuses on making the AI’s decision-making more interpretable, often via explanations [3, 67, 69] and insights into model internals [66, 70].”
Treading the Transparency Tightrope: A Taxonomy of Risks and Benefits of Foundation Model Data Transparency for Transparency Advocates
Scheuerman, M. K., Hutiri, W. T., Rahmattalabi, A., Matthews, V., Xiang, A., & Andrews, J. T. A. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790364 · Cited by 1
What Happened to Scenario-Based Design in HCI?: A Scoping Review
Carroll, J. M., Jo, J., Kim, J., Lin, Y.-F., & Chen, E. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790899 · Cited by 2
Detect, Explain, Act: How Teachers Trust and Use an Explainable Real-Time Monitoring Dashboard to Detect Student Outliers in Class
Ooge, J., Faik, A., & Verbert, K. (2026) · International Conference on Learning Analytics and Knowledge (LAK) · doi:10.1145/3785022.3785087 · Cited by 1

Authors: Anik, A. I., & Bunt, A.
Affiliations: University of Manitoba (CA)
ORCID: Anik, Ariful Islam
Bunt, Andrea
Venue: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems
Publisher: ACM
Published: 2021-05-06
Pages: 1-13
DOI: 10.1145/3411764.3445736
OpenAlex: W3160343688
Cited by: 103
References: 99
Citations by year: 2026: 12 · 2025: 17 · 2024: 29 · 2023: 30 · 2022: 12 · 2021: 3
FWCI: 8.55
Type: conference paper
Language: en
Open access: green
hdl.handle.net
Licence: www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations: CHI Conference on Human Factors in Computing Systems (publishedVersion)
Mspace (University of Manitoba) (submittedVersion)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
Keywords: training data transparency, explainable machine learning, algorithmic fairness, training data bias, stakeholder communication, formative research

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-Centric Explanations: Explaining Training Data of Machine Learning Systems to Promote Transparency

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks