The DOI matches its Crossref record; 30 of the 32 references it cites were found in a registry or an index.
The effects of example-based explanations in a machine learning interface
Open accessAbstract
The black-box nature of machine learning algorithms can make their predictions difficult to understand and explain to end-users. In this paper, we propose and evaluate two kinds of example-based explanations in the visual domain, normative explanations and comparative explanations (Figure 1), which automatically surface examples from the training set of a deep neural net sketch-recognition algorithm. To investigate their effects, we deployed these explanations to 1150 users on QuickDraw, an online platform where users draw images and see whether a recognizer has correctly guessed the intended drawing. When the algorithm failed to recognize the drawing, those who received normative explanations felt they had a better understanding of the system, and perceived the system to have higher capability. However, comparative explanations did not always improve perceptions of the algorithm, possibly because they sometimes exposed limitations of the algorithm and may have led to surprise. These findings suggest that examples can serve as a vehicle for explaining algorithmic behavior, but point to relative advantages and disadvantages of using different kinds of examples, depending on the goal.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Wang and Yin [82] found that example-based explanations underperform feature-based explanations for improving appropriate reliance, though other studies suggest example-based explanations are better at helping people detect model errors [11,13,49], usually by recognizing the dissimilarity between the instance and selected examples.”
From Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations (2023) · cites this paper as [13]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A study conducted by Cai et al. [3] found that comparative explanation, by comparisons with examples in alternative classes, can lead to better discovery of the limitations of the AI, compared to normative explanation that describes examples in the intended class.”
From Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making (2020) · cites this paper as [3]
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
"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
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 1×
“Examples can potentially help users develop intuition for the reasons underlying machine predictions, without directly exposing the internal logic of the algorithm [19, 28, 33].”
BackgroundEuropean Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · cited 1×
“The size, complexity, and opacity of ML algorithms have led to increasing regulations and demands for more explainable AI [1, 9].”
BackgroundExplaining collaborative filtering recommendations
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000) · Proceedings of the 2000 ACM conference on Computer supported cooperative work · doi:10.1145/358916.358995 · Cited by 1,731
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514
The Psychology of Social Norms.
Hankins, F. H., & Sherif, M. (1937) · American Sociological Review · doi:10.2307/2084385 · Cited by 1,468
SmoothGrad: removing noise by adding noise
Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv · doi:10.48550/arxiv.1706.03825 · Cited by 1,467
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017) · arXiv · doi:10.48550/arxiv.1711.11279 · Cited by 1,240
Self-citationThe attribution of blame : causality, responsibility, and blameworthiness
Shaver, K. G. (1985) · Cited by 800
Research works printed but not linked: 3
- Dumitru Erhan , Yoshua Bengio , Aaron Courville , and Pascal Vincent . 2009 . Visualizing higher-layer features of a deep network . University of Montreal 1341 , 3 (2009), 1 . Dumitru Erhan, Yoshua Bengio, Aaron Courville, and Pascal Vincent. 2009. Visualizing higher-layer features of a deep network. University of Montreal 1341, 3 (2009), 1.
- Tim Miller . 2017. Explanation in artificial intelligence: insights from the social sciences. arXiv preprint arXiv:1706.07269 ( 2017 ). Tim Miller. 2017. Explanation in artificial intelligence: insights from the social sciences. arXiv preprint arXiv:1706.07269 (2017). · arXiv
- Sandra Wachter Brent Mittelstadt and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. (2017). Sandra Wachter Brent Mittelstadt and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. (2017). · DOI · Paper page
Cited by
Sorted by citations
Items 201–220 of 220
المعاطى, ا. ع. م. ا. (2023) · Al-Maǧallaẗ Al-Miṣriyyaẗ Lil Dirāsāt Al-Tiǧāriyyaẗ /Al-Maǧallaẗ Al-Miṣriyyaẗ Lil Dirāsāt Al-Tiǧāriyyaẗ · doi:10.21608/alat.2023.330335
An Interpretable Machine Learning Model for Heart Arrhythmia Classification
Vedula, K. (2024) · Journal of Student Research · doi:10.47611/jsrhs.v13i1.6291
Algo-Rhythm Unplugged: Effects of Explaining Algorithmic Recommendations on Music DiscoveryPreprint
Louafi, M., & anon, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4982393
Robust Relatable Explanations of Machine Learning with Disentangled Cue-specific Saliency
Abichandani, H. S., Zhang, W., & Lim, B. Y. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712105 · Cited by 1
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
From Data to Decisions: Enhancing AI Adoption in Healthcare Through Transparent Explanations
Hassan, A. H., & bin Sulaiman, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5217-4_13
Carvallo, A., Parra, D., Brusilovsky, P. L., Valdivieso, H., Gabriel Rada, G., Donoso-Guzmán, I., & Araujo, V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-08970-0_7
Teaching AI through Object Demonstrations and Language Instructions
周中一 (2024) · Institutional Repositories DataBase (IRDB) · doi:10.15083/0002012805
From Explanation to Action: A Case Study of Agronomist Workflows
Porfírio, R. P., Santos, P. A., & Madeira, R. N. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3799333
Impact of AI Transparency Levels on Human Performance, Trust, and Workload in Collaborative Tasks
Park, G., & Kim, S.-H. (2026) · Theoretical and Applied Ergonomics · doi:10.3390/tae2020009
Lin, Y.-C., Tsai, P.-H., Weng, Y.-H., Chiu, H.-L., Ma, C.-Y., & Chang, Y.-J. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3813043
From Curiosity to Caution: How Expertise Shapes the Use of Interpretable Machine Learning
Naqvi, S., Balaji, G., Laju, A., & Kaur, H. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812376
Comprehensive Study on Shape Based Machine Learning Approaches for Visual Recognition System
Kumar, D. P., Mani, M. R., & Prasad, M. H. M. K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-30310-3_29
Domil, A. E., SĂRAC, I., Saptebani, N., & Ciprian, V. L. A. D. (2026) · Review of Management and Economic Engineering · doi:10.71235/rmee.265
Understanding Vibe Coding: A Phenomenological Investigation of Flow-Like Human-AI Collaboration
Guriță, A.-E., & Vatavu, R.-D. (2026) · International Conference on Human-AI Interaction and Experience Design (HAXD) · doi:10.1109/haxd70072.2026.11620988
Applications of Artificial Intelligence in Various Traits of Life
Hassan, S. S. (2023) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/504
Altamirano, S., Anadria, D., van der Wees, S., Tensen, P., van de Vijver, S. J. M., & Ghebreab, S. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1911214
Toward an Explainable Generative AI: Investigating User Needs Through a User-Centered Study
Alsufiani, K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-36012-0_21
AI-Driven Research Data Management
Silambarasan, G., & Shivaraj, G. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-1227-7.ch001
Metadata
- Authors
- Cai, C. J., Jongejan, J., & Holbrook, J.
- Affiliations
- Google (United States) (US)
- Venue
- Proceedings of the 24th International Conference on Intelligent User Interfaces
- Publisher
- ACM
- Published
- 2019-03-17
- Pages
- 258-262
- OpenAlex
- W2916797267
- Cited by
- 220
- References
- 32
- Citations by year
- 2026: 13 · 2025: 26 · 2024: 42 · 2023: 38 · 2022: 35 · 2021: 34 · 2020: 28 · 2019: 4
- FWCI
- 9.66
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM International Conference on Intelligent User Interfaces (IUI) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- example-based explanations, explainable machine learning, normative explanation, sketch recognition, deep neural network, black-box algorithms, QuickDraw
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
