The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Effects of Explanations in AI-Assisted Decision Making: Principles and Comparisons
Abstract
Recent years have witnessed the growing literature in empirical evaluation of explainable AI (XAI) methods. This study contributes to this ongoing conversation by presenting a comparison on the effects of a set of established XAI methods in AI-assisted decision making. Based on our review of previous literature, we highlight three desirable properties that ideal AI explanations should satisfy — improve people’s understanding of the AI model, help people recognize the model uncertainty, and support people’s calibrated trust in the model. Through three randomized controlled experiments, we evaluate whether four types of common model-agnostic explainable AI methods satisfy these properties on two types of AI models of varying levels of complexity, and in two kinds of decision making contexts where people perceive themselves as having different levels of domain expertise. Our results demonstrate that many AI explanations do not satisfy any of the desirable properties when used on decision making tasks that people have little domain expertise in. On decision making tasks that people are more knowledgeable, the feature contribution explanation is shown to satisfy more desiderata of AI explanations, even when the AI model is inherently complex. We conclude by discussing the implications of our study for improving the design of XAI methods to better support human decision making, and for advancing more rigorous empirical evaluation of XAI methods.
Overview
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
Cites
Statistics
Verification
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?
In one study, the approach of distinguishing appropriate trust, undertrust and overtrust allowed observation that feature importance and feature contribution slightly increased appropriate trust, decreased undertrust, and that for feature importance this came at the cost of a slight increase in overtrust.
“For instance in one study, this approach allowed to observe that feature importance and feature contribution slightly increased appropriate trust, decreased their undertrust, and that, for feature importance, this came at the cost of a slight increase in overtrust (Wang & Yin, 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 Wang & Yin, 2022
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
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Humans and automation: Use, misuse, disuse, abuse
Parasuraman, R., & Riley, V. (1997) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/001872097778543886 · Cited by 4,554 · cited 2×
“, the fraction of tasks where participants used a model’s prediction when it was wrong) and undertrust [25, 66] (i.”
BackgroundThe New Statistics: Why and How
Cumming, G. (2014) · Psychological Science · doi:10.1177/0956797613504966 · Cited by 3,200
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., & Elhadad, N. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2788613 · Cited by 1,685 · cited 1×
“Model-specific methods often involve the development of intrinsically interpretable models such as generalized additive models and decision sets [17, 39, 50, 77], as well as visualizing what deep neural network has learned in its intermediate layers and how its predictions are affected by different parts of the inputs…”
BackgroundThe accuracy, fairness, and limits of predicting recidivism
Dressel, J., & Farid, H. (2018) · Science Advances · doi:10.1126/sciadv.aao5580 · Cited by 1,071
Counterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
Zhang, Y., Liao, Q. V., & Bellamy, R. K. E. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372852 · Cited by 895
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445717 · Cited by 757 · cited 2×
“Finally, Desideratum 3 concerns the ultimate goal of AI-assisted decision making, that is, to maximize the joint human-AI team performance [5, 6, 11].”
BackgroundDoes the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. S. (2020) · arXiv · doi:10.48550/arxiv.2006.14779 · Cited by 754
Manipulating and Measuring Model Interpretability
Poursabzi-Sangdeh, F., Goldstein, D. G., Hofman, J. M., Wortman Vaughan, J. W., & Wallach, H. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445315 · Cited by 728
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions
Binns, R., Van Kleek, M., Veale, M., Lyngs, U., Zhao, J., & Shadbolt, N. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173951 · Cited by 691 · cited 2×
“Typical methods include asking people to rank the input data features based on their influence to overall predictions [21, 37], to indicate the direction of change in the model’s prediction when a feature’s value is altered [18, 21, 33], to simulate the model’s predictions [18, 27, 47, 54, 68], to answer “what-if” que…”
BackgroundMethodWhy and why not explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552 · cited 1×
“Earlier literature on AI explanations often concerns the communication of uncertainty in AI decisions [52, 53].”
BackgroundUnderstanding the Effect of Accuracy on Trust in Machine Learning Models
Yin, M., Wortman Vaughan, J., & Wallach, H. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300509 · Cited by 527 · cited 1×
“Following earlier literature [82, 83], we quantified people’s reliance on the model using the fraction of tasks in which the participant’s final prediction was the same as the model’s prediction (i.e., agreement fraction ).”
MethodSelf-citationBeyond Accuracy: The Role of Mental Models in Human-AI Team Performance
Bansal, G., Nushi, B., Kamar, E., Lasecki, W. S., Weld, D. S., & Horvitz, E. (2019) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v7i1.5285 · Cited by 466
The Principles and Limits of Algorithm-in-the-Loop Decision Making
Green, B., & Chen, Y. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359152 · Cited by 392 · cited 1×
“1An example of a task that may not be applicable to some decision making context is to have the human decision maker detect fairness problems of the AI model or utilize the AI model in a fair way [26, 34].”
MethodLai, V., & Tan, C. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287590 · Cited by 377
Wang, X., & Yin, M. (2021) · 26th International Conference on Intelligent User Interfaces · doi:10.1145/3397481.3450650 · Cited by 320
Self-citationExplaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders
Cheng, H.-F., Wang, R., Zhang, Z., O'Connell, F., Gray, T., Harper, F. M., & Zhu, H. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300789 · Cited by 292 · cited 3×
“Typical methods include asking people to rank the input data features based on their influence to overall predictions [21, 37], to indicate the direction of change in the model’s prediction when a feature’s value is altered [18, 21, 33], to simulate the model’s predictions [18, 27, 47, 54, 68], to answer “what-if” que…”
BackgroundMethodExplaining models: an empirical study of how explanations impact fairness judgment
Dodge, J., Liao, Q. V., Zhang, Y., Bellamy, R. K. E., & Dugan, C. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302310 · Cited by 286
The effects of example-based explanations in a machine learning interface
Cai, C. J., Jongejan, J., & Holbrook, J. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302289 · Cited by 220
McGuirl, J. M., & Sarter, N. B. (2006) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/001872006779166334 · Cited by 212
How do visual explanations foster end users' appropriate trust in machine learning?
Yang, F., Huang, Z., Scholtz, J., & Arendt, D. L. (2020) · Proceedings of the 25th International Conference on Intelligent User Interfaces · doi:10.1145/3377325.3377480 · Cited by 200
I Think I Get Your Point, AI! The Illusion of Explanatory Depth in Explainable AI
Chromik, M., Eiband, M., Buchner, F., Krüger, A., & Butz, A. (2021) · 26th International Conference on Intelligent User Interfaces · doi:10.1145/3397481.3450644 · Cited by 144
An Evaluation of the Human-Interpretability of Explanation
Lage, I., Chen, E., He, J., Narayanan, M., Kim, B., Gershman, S., & Doshi-Velez, F. (2019) · arXiv · doi:10.48550/arxiv.1902.00006 · Cited by 125 · cited 1×
“Typical methods include asking people to rank the input data features based on their influence to overall predictions [21, 37], to indicate the direction of change in the model’s prediction when a feature’s value is altered [18, 21, 33], to simulate the model’s predictions [18, 27, 47, 54, 68], to answer “what-if” que…”
Method"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
Lai, V., Liu, H., & Tan, C. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376873 · Cited by 123
Springer, A., & Whittaker, S. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302322 · Cited by 115 · cited 1×
“To this end, techniques for presenting explanations visually, selectively, and progressively [61, 73, 81], andmethods for incorporating the consideration of cognitive load into the explanation generation process [1] should be explored.”
MethodHuman Decision Making with Machine Assistance: An Experiment on Bailing and Jailing
Grgić-Hlača, N., Engel, C., & Gummadi, K. P. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359280 · Cited by 113
COGAM: Measuring and Moderating Cognitive Load in Machine Learning Model Explanations
Abdul, A., von der Weth, C., Kankanhalli, M., & Lim, B. Y. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376615 · Cited by 96
Feature-Based Explanations Don't Help People Detect Misclassifications of Online Toxicity
Carton, S., Mei, Q., & Resnick, P. (2020) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v14i1.7282 · Cited by 58
FAIRVIS: Visual Analytics for Discovering Intersectional Bias in Machine Learning
Cabrera, Á. A., Epperson, W., Hohman, F., Kahng, M., Morgenstern, J., & Chau, D. H. (2019) · 2019 IEEE Conference on Visual Analytics Science and Technology (VAST) · doi:10.1109/vast47406.2019.8986948 · Cited by 14
Flagged first, then by citations
Research works printed but not linked: 46
- 10.1145/3377325.3377519 · DOI · Paper page
- Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias. ProPublica. See https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing (2016).
- 10.1016/S0168-1699(99)00046-0 · DOI
- 10.1037/a0031354 · DOI
- 10.1145/1150402.1150464 · DOI · Paper page
- 10.1145/3377325.3377498 · DOI · Paper page
- Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Mueller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake VanderPlas, Arnaud Joly, Brian Holt, and Gaël Varoquaux. 2013. API design for machine learning software: Experiences from the scikit-learn project. In ECML PKDD Workshop: Languages for Data Mining and Machine Learning. 108–122.
- Ruth M. J. Byrne. 2019. Counterfactuals in explainable artificial intelligence (XAI): Evidence from human reasoning. In IJCAI. 6276–6282.
- Eric Chu Deb Roy and Jacob Andreas. 2020. Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction. arxiv:2007.12248 [cs.LG]. · arXiv
- 10.1177/0093854801028003005 · DOI
- 10.4324/9780203807002 · DOI
- 10.1007/978-3-319-07458-0_24 · DOI
- 10.1007/978-3-319-26633-6_13 · DOI
- 10.1145/3359786 · DOI · Paper page
- Aaron Fisher, Cynthia Rudin, and Francesca Dominici. 2019. All models are wrong, but many are useful: Learning a variable’s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn. Res. 20, 177 (2019), 1–81.
- 10.1080/10618600.2014.907095 · DOI · Paper page
- Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. Stat 1050 (2015), 9.
- 10.1145/3290605.3300809 · DOI
- Jongbin Jung, Connor Concannon, Ravi Shroff, Sharad Goel, and Daniel G. Goldstein. 2017. Simple rules for complex decisions. Available at SSRN 2919024 (2017).
- Daniel Kahneman. 2011. Thinking, Fast and Slow. Macmillan.
- 10.1016/j.artint.2021.103459 · DOI · Paper page
- Been Kim, Rajiv Khanna, and Oluwasanmi O. Koyejo. 2016. Examples are not enough, learn to criticize! Criticism for interpretability. In Advances in Neural Information Processing Systems. 2280–2288.
- Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, et al. 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV). In International Conference on Machine Learning. PMLR, 2668–2677.
- John Logan Koepke and David G. Robinson. 2018. Danger ahead: Risk assessment and the future of bail reform. Wash. L. Rev. 93 (2018), 1725.
- Josua Krause, Adam Perer, and Enrico Bertini. 2018. A user study on the effect of aggregating explanations for interpreting machine learning models. In ACM KDD Workshop on Interactive Data Exploration and Analytics.
- 10.1145/2939672.2939874 · DOI · Paper page
- Jeff Larson, Surya Mattu, Lauren Kirchner, and Julia Angwin. 2016. How we analyzed the COMPAS recidivism algorithm. ProPublica (5 2016) 9, 1 (2016).
- 10.1145/2030112.2030168 · DOI · Paper page
- Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems. 4765–4774.
- 10.1109/IRI.2017.89 · DOI
- 10.4018/IJMDEM.2018010101 · DOI
- Maranda McBride and Shona Morgan. 2010. Trust calibration for automated decision aids. Institute for Homeland Security Solutions. [Online]. Available: https://www.ihssnc.org/portals/0/Documents/VIMSDocuments/McBride_Research_Brief.pdf.
- 10.1177/0018720814561675 · DOI · Paper page
- Christoph Molnar. 2019. Interpretable Machine Learning.
- 10.1016/S0020-7373(87)80013-5 · DOI
- Barbara A. Oakley. 2014. A Mind for Numbers: How to Excel at Math and Science (Even if you Flunked Algebra). TarcherPerigee.
- Bernie J. O’Brien. 1989. Words or numbers? The evaluation of probability expressions in general practice. The Journal of the Royal College of General Practitioners 39, 320 (1989), 98–100.
- 10.5555/1953048.2078195 · DOI
- Amir Hossein Akhavan Rahnama and Henrik Boström. 2019. A study of data and label shift in the LIME framework. arXiv preprint arXiv:1910.14421. · arXiv
- 10.1145/2939672.2939778 · DOI · Paper page
- 10.1207/s15516709cog2605_1 · DOI · Paper page
- Richard Tomsett, Dave Braines, Dan Harborne, Alun Preece, and Supriyo Chakraborty. 2018. Interpretable to whom? A role-based model for analyzing interpretable machine learning systems. arXiv preprint arXiv:1806.07552. · arXiv
- Jennifer Wortman Vaughan and Hanna Wallach. 2020. A human-centered agenda for intelligible machine learning. Machines We Trust: Getting Along with Artificial Intelligence (2020).
- Fulton Wang and Cynthia Rudin. 2015. Falling rule lists. In Artificial Intelligence and Statistics. 1013–1022.
- 10.14507/er.v23.1970 · DOI
- Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International Conference on Machine Learning. 2048–2057.
Cited by
Sorted by citations
What large language models know and what people think they know
Steyvers, M., Tejeda, H., Kumar, A., Belem, C., Karny, S., Hu, X., Mayer, L. W., & Smyth, P. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-024-00976-7 · Cited by 209
Wischnewski, M., Krämer, N., & Müller, E. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581197 · Cited by 146
Wang, P., & Ding, H. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103732 · Cited by 68
Visser, R., Peters, T. M., Scharlau, I., & Hammer, B. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101357 · Cited by 58
Integrity-based Explanations for Fostering Appropriate Trust in AI Agents
Mehrotra, S., Jorge, C. C., Jonker, C. M., & Tielman, M. L. (2024) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3610578 · Cited by 51
Raees, M., Khan, V.-J., Lykourentzou, I., & Papangelis, K. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791467 · Cited by 5
Metadata
- Authors
- Wang, X., & Yin, M.
- Affiliations
- Purdue University, Indiana, USA
- Venue
- ACM Transactions on Interactive Intelligent Systems
- Published
- 2022-11-04
- Volume
- 12
- Issue
- 4
- Pages
- 1-36
- ISSN
- 2160-6455
- 2160-6463
- Cited by
- 74
- References
- 34
- Language
- en
- Funders
- National Science Foundation (IIS-1850335)
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
