The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
You Can Only Verify When You Know the Answer: Feature-Based Explanations Reduce Overreliance on AI for Easy Decisions, but Not for Hard Ones
Abstract
Explaining the mechanisms behind model predictions is a common strategy in AI-assisted decision-making to help users rely appropriately on AI. However, recent research shows that the effectiveness of explanations depends on numerous factors, leading to mixed results, with many studies finding no effect or even an increase in overreliance, while explanations do improve appropriate reliance in other studies. We consider the factor of decision difficulty to better understand when feature-based explanations can mitigate overreliance. To this end, we conducted an online experiment (N = 200) with carefully selected task instances that cover a wide range of difficulties. We found that explanations reduce overreliance for easy decisions, but that this effect vanishes with increasing decision difficulty. For the most difficult decisions, explanations might even increase overreliance. Our results imply that explanations of the model’s inner workings are only helpful for a limited set of decision tasks where users easily know the answer themselves.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
"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
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“Post-hoc methods are criticized for their lack of faithfulness to how the model actually works and for being not informative enough to support decision-making [31], but are often used due to the difficulty of building inherently interpretable models for complex tasks.”
Buçinca, Z., Malaya, M. B., & Gajos, K. Z. (2021) · arXiv · doi:10.48550/arxiv.2102.09692 · Cited by 1,124
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 3×
“However, many studies have found that explanations do not effectively improve appropriate reliance [3, 33, 38, 41] or even increase overreliance on AI [2, 4, 17, 21, 34], i.e., people become more likely to adopt detrimental AI recommendations.”
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
Abdul, A., Vermeulen, J., Wang, D., Lim, B. Y., & Kankanhalli, M. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174156 · Cited by 743
The Role of Explanations on Trust and Reliance in Clinical Decision Support Systems
Bussone, A., Stumpf, S., & O'Sullivan, D. (2015) · 2015 International Conference on Healthcare Informatics · doi:10.1109/ichi.2015.26 · Cited by 441
Explanations Can Reduce Overreliance on AI Systems During Decision-Making
Vasconcelos, H., Jörke, M., Grunde-McLaughlin, M., Gerstenberg, T., Bernstein, M. S., & Krishna, R. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579605 · Cited by 402
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×
“…the goal is to improve human decision-making in difficult high-stakes decisions, such as medical diagnosis [4, 17], creditworthiness assessment [16], or recidivism prediction [24, 38], where the call for explainability is particularly prominent and at the same time, overreliance is especially…”
Research works printed but not linked: 2
- Zana Buçinca, Alexandra Chouldechova, Jennifer Wortman Vaughan, and Krzysztof Z. Gajos. 2022. Beyond end predictions: stop putting machine learning first and design human-centered AI for decision support. In Virtual Workshop on Human-Centered AI Workshop at NeurIPS (HCAI @ NeurIPS ’22). Virtual Event, USA, 1–4.
- Sean Koon. 2022. A human-capabilities orientation for human-AI interaction design. In Virtual Workshop on Human-Centered AI Workshop at NeurIPS (HCAI @ NeurIPS ’22). Virtual Event, USA, 1–5.
Cited by
Personalising AI Assistance Based on Overreliance Rate in AI-Assisted Decision Making
Swaroop, S., Buçinca, Z., Gajos, K. Z., & Doshi-Velez, F. (2025) · Proceedings of the 30th International Conference on Intelligent User Interfaces · doi:10.1145/3708359.3712128 · Cited by 20
Morey, D. A., Rayo, M. F., & Woods, D. D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01784-y · Cited by 35
“Our fi ndingsaddtogrowing concerns about the effectiveness of explainable AI to reliably help people recognize and recover from AI errors 26,29,47,48,52 – 54 .”
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 15
Kokje, E., Lermer, E., Kleine, A., & Gaube, S. (2026) · Cognitive Research Principles and Implications · doi:10.1186/s41235-026-00707-z · Cited by 5
“A potential solution in the form of explainability, wherein additional information about the AI’s prediction is provided, has been proposed to overcome this issue (Vasconcelos et al., 2023) but has shown very mixed results (Zhang et al., 2024).”
Tadson, B., Krisam, C., & Mädche, A. (2025) · Lecture notes in information systems and organisation · doi:10.1007/978-3-032-00815-2_14 · Cited by 1
Metadata
- Authors
- Zhang, Z. T., Buchner, F., Liu, Y., & Butz, A.
- Affiliations
- Fortiss (DE)
- Ludwig-Maximilians-Universität München (DE)
- Venue
- Proceedings of Mensch und Computer 2024
- Publisher
- ACM
- Published
- 2024-09
- Pages
- 156-170
- OpenAlex
- W4401887840
- Cited by
- 6
- References
- 44
- Citations by year
- 2026: 1 · 2025: 5
- FWCI
- 1.73
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Mensch und Computer (MuC) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Keywords
- feature-based explanations, overreliance on AI, AI-assisted decision-making, decision difficulty, explainable AI, trust in AI, human-AI interaction, model interpretability
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: You Can Only Verify When You Know the Answer: Feature-Based Explanations Reduce Overreliance on AI for Easy Decisions, but Not for Hard Ones. https://app.cochat.ai/papers/10.1145/3670653.3670660
- The paper
- Zhang, Z. T., Buchner, F., Liu, Y., & Butz, A. (2024). You Can Only Verify When You Know the Answer: Feature-Based Explanations Reduce Overreliance on AI for Easy Decisions, but Not for Hard Ones. Proceedings of Mensch und Computer 2024. https://doi.org/10.1145/3670653.3670660
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.