The Impact of Imperfect XAI on Human-AI Decision-Making
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Explainability techniques are rapidly being developed to improve human-AI decision-making across various cooperative work settings. Consequently, previous research has evaluated how decision-makers collaborate with imperfect AI by investigating appropriate reliance and task performance with the aim of designing more human-centered computer-supported collaborative tools. Several human-centered explainable AI (XAI) techniques have been proposed in hopes of improving decision-makers' collaboration with AI; however, these techniques are grounded in findings from previous studies that primarily focus on the impact of incorrect AI advice. Few studies acknowledge the possibility of the explanations being incorrect even if the AI advice is correct. Thus, it is crucial to understand how imperfect XAI affects human-AI decision-making. In this work, we contribute a robust, mixed-methods user study with 136 participants to evaluate how incorrect explanations influence humans' decision-making behavior in a bird species identification task, taking into account their level of expertise and an explanation's level of assertiveness. Our findings reveal the influence of imperfect XAI and humans' level of expertise on their reliance on AI and human-AI team performance. We also discuss how explanations can deceive decision-makers during human-AI collaboration. Hence, we shed light on the impacts of imperfect XAI in the field of computer-supported cooperative work and provide guidelines for designers of human-AI collaboration systems.
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.
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
Seeking Qualitative Rigor in Inductive Research: Notes on the Gioia Methodology
Gioia, D. A., Corley, K. G., & Hamilton, A. L. (2013) · Organizational Research Methods · doi:10.1177/1094428112452151 · Cited by 13,227
Prolific.ac—A subject pool for online experiments
Palan, S., & Schitter, C. (2018) · Journal of Behavioral and Experimental Finance · doi:10.1016/j.jbef.2017.12.004 · Cited by 3,450 · cited 1×
“Additionally, we use Prolific as previous research has indicated that this platform is a reliable source of research data [63, 66].”
MethodBeyond the Turk: Alternative platforms for crowdsourcing behavioral research
Peer, E., Brandimarte, L., Samat, S., & Acquisti, A. (2017) · Journal of Experimental Social Psychology · doi:10.1016/j.jesp.2017.01.006 · Cited by 2,957 · cited 1×
“Additionally, we use Prolific as previous research has indicated that this platform is a reliable source of research data [63, 66].”
MethodDoes 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 3×
“, [6, 29, 31]), we can calculate the human-AI team performance to determine if CTP exists.”
BackgroundMethodDoes 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
Perspectives in machine learning for wildlife conservation
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., van Langevelde, F., Burghardt, T., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-27980-y · Cited by 740
Cai, C. J., Winter, S., Steiner, D., Wilcox, L., & Terry, M. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359206 · Cited by 594
Grounded Copilot: How Programmers Interact with Code-Generating Models
Barke, S., James, M. B., & Polikarpova, N. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3586030 · Cited by 436 · cited 1×
“Unlike Calisto et al. [18], our experiment collects the human’s initial decision before showing the AI’s advice to the human, allowing us to measure appropriate reliance and assess for complementary team performance.”
BackgroundGitHub Copilot AI pair programmer: Asset or Liability?
Moradi Dakhel, A., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., & Jiang, Z. M. (. (2023) · Journal of Systems and Software · doi:10.1016/j.jss.2023.111734 · Cited by 417
GitHub Copilot AI pair programmer: Asset or Liability?
Dakhel, A. M., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., Ming, Z., & Jiang (2022) · arXiv · doi:10.48550/arxiv.2206.15331 · Cited by 417 · cited 2×
“A similar study shows clinicians with various levels of expertise four different types of explanations, including visual, example-based explanations [83].”
BackgroundThe 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 2×
“The structure of phases one and two are corroborated with previous work [30].”
ResultHuman-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI
Wang, D., Weisz, J. D., Muller, M., Ram, P., Geyer, W., Dugan, C., Tausczik, Y., Samulowitz, H., & Gray, A. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359313 · Cited by 342 · cited 1×
“CSCW, and more specifically human-AI collaboration, is prevalent across high-stakes scenarios [16, 49, 75, 80].”
BackgroundThe perils and pitfalls of explainable AI: Strategies for explaining algorithmic decision-making
de Bruijn, H., Warnier, M., & Janssen, M. (2022) · Government Information Quarterly · doi:10.1016/j.giq.2021.101666 · Cited by 264 · cited 1×
“RAIR comprises the cases in which the human corrects their initially incorrect decision by overriding it with the correct AI advice.”
BackgroundHelp Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
Kim, S. S. Y., Watkins, E. A., Russakovsky, O., Fong, R., & Monroy-Hernández, A. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581001 · Cited by 233
Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Chen, V., Liao, Q. V., Wortman Vaughan, J., & Bansal, G. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3610219 · Cited by 220 · cited 5×
“These types of scenarios should not be overlooked when investigating human-AI collaborations in work settings.”
BackgroundInfluentialThe 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 · cited 4×
“Cai et al. [16] propose normative and comparative explanations, different types of example-based explanations.”
BackgroundMethodInfluentialAppropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations
Schemmer, M., Kuehl, N., Benz, C., Bartos, A., & Satzger, G. (2023) · Proceedings of the 28th International Conference on Intelligent User Interfaces · doi:10.1145/3581641.3584066 · Cited by 208 · cited 9×
“The original dataset consists of 11,788 images of 200 different bird species and is split into 5,994 training and 5,794 test images.”
BackgroundMethodInfluentialHow 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 · cited 2×
“We simplified the correctness of XAI advice to be a binary case of correct or incorrect in Figure 1.”
BackgroundMethodVisual, textual or hybrid: the effect of user expertise on different explanations
Szymanski, M., Millecamp, M., & Verbert, K. (2021) · 26th International Conference on Intelligent User Interfaces · doi:10.1145/3397481.3450662 · Cited by 131
Artificial intelligence in the workplace -- a double-edged sword
Wilkens, U. (2020) · The International Journal of Information and Learning Technology · doi:10.1108/ijilt-02-2020-0022 · Cited by 117
Human-Centered Explainable AI (HCXAI): Beyond Opening the Black-Box of AI
Ehsan, U., Wintersberger, P., Liao, Q. V., Watkins, E. A., Manger, C., Daumé III, H., Riener, A., & Riedl, M. O. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3503727 · Cited by 117
Dikmen, M., & Burns, C. (2022) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2022.102792 · Cited by 116 · cited 3×
“There has been a growing interest in understanding the impact that the decision-maker’s domain expertise has on human-AI collaborations [10, 17, 22, 27, 54, 55, 72, 75, 90].”
BackgroundInfluentialNourani, M., King, J., & Ragan, E. (2020) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v8i1.7469 · Cited by 116
The role of domain expertise in trusting and following explainable AI decision support systems
Bayer, S., Gimpel, H., & Markgraf, M. (2022) · Journal of Decision Systems · doi:10.1080/12460125.2021.1958505 · Cited by 103
A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making
Schemmer, M., Hemmer, P., Nitsche, M., Kühl, N., & Vössing, M. (2022) · Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3514094.3534128 · Cited by 91 · cited 3×
“Experts and non-experts interacting with the same imperfect AI and the same type of explanations in human-AI collaboration scenarios, such as decision-making [73] or learning systems [79], could result in some users misunderstanding or inappropriately relying on/overriding the AI advice.”
BackgroundSelf-citationImproving Human-AI Collaboration With Descriptions of AI Behavior
Cabrera, Á. A., Perer, A., & Hong, J. I. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579612 · Cited by 87
Self-citationFok, R., & Weld, D. S. (2024) · AI Magazine · doi:10.1002/aaai.12182 · Cited by 81
Levy, A., Agrawal, M., Satyanarayan, A., & Sontag, D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445522 · Cited by 73 · cited 1×
“Hypothesis 2: The correctness of explanations impacts humans’ relative self-reliance in human-AI decision-making.”
BackgroundFaithful AI in Medicine: A Systematic Review with Large Language Models and Beyond
Xie, Q., Schenck, E. J., Yang, H. S., Chen, Y., Peng, Y., & Wang, F. (2023) · doi:10.21203/rs.3.rs-3661764/v1 · Cited by 57
Du, Y., Antoniadi, A. M., McNestry, C., McAuliffe, F. M., & Mooney, C. (2022) · Applied Sciences · doi:10.3390/app122010323 · Cited by 47 · cited 3×
“00, example-based: p-value = 0 .”
BackgroundGrounded Copilot: How Programmers Interact with Code-Generating Models
Barke, S., James, M. B., & Polikarpova, N. (2022) · arXiv · doi:10.48550/arxiv.2206.15000 · Cited by 23 · cited 1×
“Unlike Calisto et al. [18], our experiment collects the human’s initial decision before showing the AI’s advice to the human, allowing us to measure appropriate reliance and assess for complementary team performance.”
BackgroundOn the Interdependence of Reliance Behavior and Accuracy in AI-Assisted Decision-Making
Schoeffer, J., Jakubik, J., Voessing, M., Kuehl, N., & Satzger, G. (2023) · Frontiers in Artificial Intelligence and Applications · doi:10.3233/faia230074 · Cited by 15
Cited by
Peng, L., Li, D., Zhang, Z., Zhang, T., Huang, A., Yang, S., & Hu, Y. (2024) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2024.103629 · Cited by 59
Visser, R., Peters, T. M., Scharlau, I., & Hammer, B. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101357 · Cited by 58
“…2021; Bussone et al., 2015; Chen et al., 2023; He et al., 2023; Klingbeil et al., 2024; Körber et al., 2018; Lu & Yin, 2021; Miller et al., 2016; Morrison et al., 2024; Naiseh et al., 2023; Schemmer et al., 2023; Schmidt & Biessmann, 2019; Vasconcelos et al., 2023; Vered et al., 2023; Wang &…”
InfluentialHuman Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information
Spitzer, P., Holstein, J., Hemmer, P., Vössing, M., Kühl, N., Martin, D., & Satzger, G. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3710999 · Cited by 18
Self-citationMastrianni, A., Kim, M. S., Sullivan, T. M., Sippel, G. J., Burd, R. S., Gajos, K. Z., & Sarcevic, A. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757512 · Cited by 6
“Recommendations made by the system earlier in the medical event may be more likely to affect decision making and prevent teams from pursuing incorrect goals (e.g., preparing blood transfusion for a patient that does not need one).”
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
- Morrison, K., Spitzer, P., Turri, V., Feng, M., Kühl, N., & Perer, A.
- Venue
- Proceedings of the ACM on Human-Computer Interaction
- Published
- 2024-04-17
- Volume
- 8
- Issue
- CSCW1
- Pages
- 1-39
- ISSN
- 2573-0142 (ISSN-L)
- OpenAlex
- W4396218607
- Cited by
- 60
- References
- 32
- FWCI
- 8.93
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.