How Stated Accuracy of an AI System and Analogies to Explain Accuracy Affect Human Reliance on the System
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
AI systems are increasingly being used to support human decision making. It is important that AI advice is followed appropriately. However, according to existing literature, users typically under-rely or over-rely on AI systems, and this leads to sub-optimal team performance. In this context, we investigate the role of stated system accuracy by contrasting the lack of system information with the presence of system accuracy in a loan prediction task. We explore how the degree to which humans understand system accuracy influences their reliance on the AI system, by investigating numeracy levels and with the aid of analogies to explain system accuracy in a first of its kind between-subjects study (N=281). We found that explaining the stated accuracy of a system using analogies failed to help users rely on the AI systemappropriately (i.e., the tendency of users to rely on the system when the system is correct, or on themselves otherwise). To eliminate the impact of subjective attitudes towards analogy domains, we conducted a within-subjects study (N=248) where each participant worked on tasks with analogy-based explanations from different domains. Results from this second study confirmed that explaining stated accuracy of the system with analogies was not sufficient to facilitate appropriate reliance on the AI system in the context of loan prediction tasks, irrespective of individual user differences. Based on our findings from the two studies, we reason that the under-reliance on the AI system may be a result of users' overestimation of their own ability to solve the given task. Thus, although familiar analogies can be effective in improving the intelligibility of stated accuracy of the system, an improved understanding of system accuracy does not necessarily lead to improved system reliance and team performance.
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
Algorithm aversion: People erroneously avoid algorithms after seeing them err.
Dietvorst, B. J., Simmons, J. P., & Massey, C. (2015) · Journal of Experimental Psychology: General · doi:10.1037/xge0000033 · Cited by 3,232 · cited 2×
“For example, Dietvorst et al. [11] and Dzindolet et al. [13] found that users stop relying on a system after seeing it make a mistake.”
BackgroundResultAlgorithm appreciation: People prefer algorithmic to human judgment
Logg, J. M., Minson, J. A., & Moore, D. A. (2019) · Organizational Behavior and Human Decision Processes · doi:10.1016/j.obhdp.2018.12.005 · Cited by 2,061
Dietvorst, B. J., Simmons, J. P., & Massey, C. (2018) · Management Science · doi:10.1287/mnsc.2016.2643 · Cited by 1,230
McDonald, N., Schoenebeck, S., & Forte, A. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359174 · Cited by 1,206
Measuring Numeracy without a Math Test: Development of the Subjective Numeracy Scale
Fagerlin, A., Zikmund-Fisher, B. J., Ubel, P. A., Jankovic, A., Derry, H. A., & Smith, D. M. (2007) · Medical Decision Making · doi:10.1177/0272989x07304449 · Cited by 960 · cited 1×
“To do so we used the Subjective Numeracy Scale [16, 68], which has been widely validated as a measure for numeracy level in risk perception literature.”
MethodZhang, 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
Franke, T., Attig, C., & Wessel, D. (2019) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2018.1456150 · Cited by 828 · cited 3×
“Likewise, general affinity to technology ( ATI ) had a significant effect on subjective feeling of understanding the system ( TiA-U/P ) and trusting the intentions of the designers ( TiA-IoD ).”
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 1×
“[1] observed that explanations can promote blind trust rather than lead to appropriate reliance on AI systems.”
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
'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 1×
“The loan prediction task has been widely used to study human-AI decision making where there is a clear risk associated with the decision and a potential benefit in adopting AI advice [5, 9, 27, 60].”
Background
Cited by
Kim, S. S. Y., Vaughan, J. W., Liao, Q. V., Lombrozo, T., & Russakovsky, O. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714020 · Cited by 58
“Prior work has investigated how providing information about an AI system’s accuracy [43, 128, 129] and (un)certainty [6, 14, 17, 41, 132], explanations of outputs [6, 14, 17, 40, 41, 69, 132], and onboarding materials [18, 68] impact user reliance, as well as the roles played by human intuition…”
Visser, R., Peters, T. M., Scharlau, I., & Hammer, B. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101357 · Cited by 58
“…2022; Wanner et al., 2020), switch rate (Chen et al., 2023; Leffrang & Müller, 2021; Naiseh et al., 2023), advice adoption (Bansal et al., 2021; He et al., 2023; Jiang et al., 2022; Klingbeil et al., 2024; Wang & Yin, 2023), agreement rate (Chen et al., 2023; Naiseh et al., 2023; Nourani et…”
InfluentialHe, G., Demartini, G., & Gadiraju, U. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713218 · Cited by 23
Self-citationRaees, 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
“…[33], RAIR [13, 60–63, 103, 127, 131, 132, 145], RSR [13, 60–63, 103, 127, 131, 132], AI Safety [13], Deception of Reliance [103], Accuracy-wid [60, 62, 63, 98, 127] Trust Subjective Trust Rating [8–10, 18, 23, 43, 76, 83, 88, 94, 96, 97, 102, 151, 164, 167, 168, 170], Trust in Automation [22, 40,…”
InfluentialFrom Trust to Appropriate Reliance: Measurement Constructs in Human-AI Decision-Making
Raees, M., & Papangelis, K. (2026) · arXiv · doi:10.48550/arxiv.2604.23896 · Cited by 5
“Likewise, Accuracy-wid [33] (accuracy with initial disagreement – 5 studies) is used to capture users’ appropriate reliance when they disagree with the AI advice initially.”
Metadata
- Authors
- He, G., Buijsman, S., & Gadiraju, U.
- Venue
- Proceedings of the ACM on Human-Computer Interaction
- Published
- 2023-09-28
- Volume
- 7
- Issue
- CSCW2
- Pages
- 1-29
- ISSN
- 2573-0142 (ISSN-L)
- OpenAlex
- W4387328606
- Cited by
- 39
- References
- 27
- FWCI
- 3.43
- 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.