Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
Interpretability methods aim to help users build trust in and understand the capabilities of machine learning models. However, existing approaches often rely on abstract, complex visualizations that poorly map to the task at hand or require non-trivial ML expertise to interpret. Here, we present two interface modules that facilitate intuitively assessing model reliability. To help users better characterize and reason about a model’s uncertainty, we visualize raw and aggregate information about a given input’s nearest neighbors. Using an interactive editor, users can manipulate this input in semantically-meaningful ways, determine the effect on the output, and compare against their prior expectations. We evaluate our approach using an electrocardiogram beat classification case study. Compared to a baseline feature importance interface, we find that 14 physicians are better able to align the model’s uncertainty with domain-relevant factors and build intuition about its capabilities and limitations.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605 · cited 3×
“This idea manifests in theories of HCI stating that effective and engaging interfaces should allow users to view and interact with them in a way that feels direct — i.e., the visualizations and interactive mechanisms available to users should align with their cognitive chunks.”
MethodResultExplaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507 · cited 1×
“The growing field of ML interpretability aims to provide information that helps people understand how a particular model works, either on a global or case-by-case level [18].”
BackgroundMachine Learning Interpretability: A Survey on Methods and Metrics
Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019) · Electronics · doi:10.3390/electronics8080832 · Cited by 1,842 · cited 1×
“A major area of focus has been on developing methodologies for computing such explanations [14].”
BackgroundFairness and Abstraction in Sociotechnical Systems
Selbst, A. D., Boyd, D., Friedler, S. A., Venkatasubramanian, S., & Vertesi, J. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287598 · Cited by 1,631
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · cited 2×
“With respect to example-based explanations, the visualizations used in papers are often a table of features if the data is tabular [37, 56, 57] or a list of images if the data is image-based [9, 27, 28].”
BackgroundTechniques for Interpretable Machine Learning
Du, M., Liu, N., & Hu, X. (2018) · arXiv · doi:10.48550/arxiv.1808.00033 · Cited by 1,261
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
Explaining machine learning classifiers through diverse counterfactual explanations
Mothilal, R. K., Sharma, A., & Tan, C. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372850 · Cited by 1,233 · cited 1×
“Here, methods that generate counterfactual examples (i.e., similar example(s) that are classified differently) [21,47,64] might provide useful inspiration.”
MethodCounterfactual 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
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
Liao, Q. V., Gruen, D., & Miller, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376590 · Cited by 925
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 · cited 2×
“Even methods that are intended to be simpler and more understandable to such users, such as reporting feature weights or displaying more information about the model and dataset, have not improved decision-making in experimental studies [8, 30, 43, 53].”
BackgroundMethodManipulating and Measuring Model Interpretability
Poursabzi-Sangdeh, F., Goldstein, D. G., Hofman, J. M., Vaughan, J. W., & Wallach, H. (2018) · arXiv · doi:10.48550/arxiv.1802.07810 · Cited by 711
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
Principles of Explanatory Debugging to Personalize Interactive Machine Learning
Kulesza, T., Burnett, M., Wong, W.-K., & Stumpf, S. (2015) · Proceedings of the 20th International Conference on Intelligent User Interfaces · doi:10.1145/2678025.2701399 · Cited by 576
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Jacovi, A., Marasović, A., Miller, T., & Goldberg, Y. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445923 · Cited by 545 · cited 3×
“Indeed, research on human trust suggests that in addition to conveying assurances of certainty, acknowledging when systems are uncertain is also an important factor in building effective trust [35].”
BackgroundMethodDo as AI say: susceptibility in deployment of clinical decision-aids
Gaube, S., Suresh, H., Raue, M., Merritt, A., Berkowitz, S. J., Lermer, E., Coughlin, J. F., Guttag, J. V., Colak, E., & Ghassemi, M. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00385-9 · Cited by 543 · cited 2×
“Drawing from prior work in cognitive and social psychology [24, 51, 60, 61], case-based reasoning [1], sociology [35], and HCI [7, 14, 30, 32, 44, 45, 56, 72], we identify several design sub-goals to this end:”
MethodResultSelf-citationThe 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
Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making
Cai, C. J., Reif, E., Hegde, N., Hipp, J., Kim, B., Smilkov, D., Wattenberg, M., Viegas, F., Corrado, G. S., Stumpe, M. C., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300234 · Cited by 405
Lai, V., & Tan, C. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287590 · Cited by 377
What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
Tonekaboni, S., Joshi, S., McCradden, M. D., & Goldenberg, A. (2019) · arXiv · doi:10.48550/arxiv.1905.05134 · Cited by 318
Proxy tasks and subjective measures can be misleading in evaluating explainable AI systems
Buçinca, Z., Lin, P., Gajos, K. Z., & Glassman, E. L. (2020) · Proceedings of the 25th International Conference on Intelligent User Interfaces · doi:10.1145/3377325.3377498 · Cited by 307
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 · cited 2×
“With respect to example-based explanations, the visualizations used in papers are often a table of features if the data is tabular [37, 56, 57] or a list of images if the data is image-based [9, 27, 28].”
BackgroundHuman factors in model interpretability: Industry practices, challenges, and needs
Hong, S. R., Hullman, J., & Bertini, E. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3392878 · Cited by 219
Automated and interpretable patient ECG profiles for disease detection, tracking, and discovery
Tison, G. H., Zhang, J., Delling, F. N., & Deo, R. C. (2019) · Circulation: Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.118.005289 · Cited by 208
Carter, S., Armstrong, Z., Schubert, L., Johnson, I., & Olah, C. (2019) · Distill · doi:10.23915/distill.00015 · Cited by 147
Xie, Y., Chen, M., Kao, D., Gao, G., & Chen, X. '. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376807 · Cited by 141
Designing Contestability: Interaction Design, Machine Learning, and Mental Health
Hirsch, T., Merced, K., Narayanan, S., Imel, Z. E., & Atkins, D. C. (2017) · Proceedings of the 2017 Conference on Designing Interactive Systems · doi:10.1145/3064663.3064703 · Cited by 110 · cited 3×
“, to make questioning and probing the model an integrated part of the system, rather than an “out-of-band activity” [30, 56].”
BackgroundMethodMisplaced Trust: Measuring the Interference of Machine Learning in Human Decision-Making
Suresh, H., Lao, N., & Liccardi, I. (2020) · 12th ACM Conference on Web Science · doi:10.1145/3394231.3397922 · Cited by 49
Self-citationMulligan, D. K., Kluttz, D., & Kohli, N. (2019) · doi:10.2139/ssrn.3311894 · Cited by 32 · cited 3×
“, to make questioning and probing the model an integrated part of the system, rather than an “out-of-band activity” [30, 56].”
BackgroundMethod
Cited by
Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
Rong, Y., Leemann, T., Nguyen, T.-T., Fiedler, L., Qian, P., Unhelkar, V., Seidel, T., Kasneci, G., & Kasneci, E. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3331846 · Cited by 278
Gomez, C., Cho, S. M., Ke, S., Huang, C.-M., & Unberath, M. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1521066 · Cited by 209
Bias and ethics of AI systems applied in auditing - A systematic review
Murikah, W., Nthenge, J. K., & Musyoka, F. M. (2024) · Scientific African · doi:10.1016/j.sciaf.2024.e02281 · Cited by 148
“Deployed models perpetuate stereotypes and societal prejudices, presenting biased outcomes under the guise of impartial algorithmic determinations [56].”
Bertrand, A., Viard, T., Belloum, R., Eagan, J. R., & Maxwell, W. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581314 · Cited by 71
Kim, T. S., Lee, Y., Chang, M., & Kim, J. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606833 · Cited by 56
Metadata
- Authors
- Suresh, H., Lewis, K. M., Guttag, J., & Satyanarayan, A.
- Venue
- 27th International Conference on Intelligent User Interfaces
- Publisher
- ACM
- Published
- 2022-03-22
- Pages
- 767-781
- OpenAlex
- W3130185945
- Cited by
- 20
- References
- 30
- FWCI
- 2.85
- Type
- conference paper
- 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.