Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked to use ML predictions to make high-stakes decisions. Multiple ML usability challenges can appear as result, such as lack of user trust in the model, inability to reconcile human-ML disagreement, and ethical concerns about oversimplification of complex problems to a single algorithm output. In this paper, we investigate the ML usability challenges that present in the domain of child welfare screening through a series of collaborations with child welfare screeners. Following the iterative design process between the ML scientists, visualization researchers, and domain experts (child screeners), we first identified four key ML challenges and honed in on one promising explainable ML technique to address them (local factor contributions). Then we implemented and evaluated our visual analytics tool, Sibyl, to increase the interpretability and interactivity of local factor contributions. The effectiveness of our tool is demonstrated by two formal user studies with 12 non-expert participants and 13 expert participants respectively. Valuable feedback was collected, from which we composed a list of design implications as a useful guideline for researchers who aim to develop an interpretable and interactive visualization tool for ML prediction models deployed for child welfare screeners and other similar domain experts.
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.
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
“For structured data XAI, challenges include managing cognitive overload from long lists of features and assessing the plausibility of abstract feature importance scores, which may be statistically powerful but counter-intuitive to a clinician [83].”
From Explainable AI for Clinical Decision Support Systems: Literature Review, Key Gaps, and Research Synthesis (2025) · cites this paper as [83]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In contrast, XAI for structured EHR data relies on feature attribution (e.g., using SHAP or LIME), answering the question, 'What factors influenced this prediction?' [83].”
From Explainable AI for Clinical Decision Support Systems: Literature Review, Key Gaps, and Research Synthesis (2025) · cites this paper as [83]
Experimental — accuracy not yet measured
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
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 1×
“The local factor contributions were found using the Shapely Additive Explanations (SHAP) algorithm [14].”
MethodGauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“Simple models, such as regression, are often cited as being inherently interpretable [20].”
BackgroundLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 1×
“A common explanation need addressed by the literature [13] is to understand how the model works (model transparency), possibly for debugging.”
BackgroundTowards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121 · cited 6×
“Doshi-Velez and Kim [2] also define three evaluation approaches for ML interpretability.”
BackgroundInfluentialModeling Tabular data using Conditional GANPreprint
Xu, L., Skoularidou, M., Cuesta‐Infante, A., & Veeramachaneni, K. K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.00503 · Cited by 2,783 · cited 1×
“Data for different factors was generated using the CTGAN synthetic data generation algorithm [26], in which a generative model is learned from the real data and samples that resemble the real data are drawn from the model.”
MethodSelf-citationExplainable machine-learning predictions for the prevention of hypoxaemia during surgery
Lundberg, S. M., Nair, B., Vavilala, M. S., Horibe, M., Eisses, M. J., Adams, T., Liston, D. E., Low, D. K.-W., Newman, S.-F., Kim, J., et al. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0304-0 · Cited by 1,967
Fisher, A., Rudin, C., & Dominici, F. (2018) · arXiv · doi:10.48550/arxiv.1801.01489 · Cited by 1,165 · cited 1×
“The global factor importance rankings were found using the Permutation Importance algorithm [3].”
MethodDesigning Theory-Driven User-Centric Explainable AI
Wang, D., Yang, Q., Abdul, A., & Lim, B. Y. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300831 · Cited by 906 · cited 4×
“[25] introduced a list of the cognitive biases explanations can help address.”
BackgroundInfluentialA Nested Model for Visualization Design and Validation
Munzner, T. (2009) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2009.111 · Cited by 880 · cited 1×
“…RQ2 (identifying helpful interfaces) and RQ3 (identifying important design choices), and based on the usability challenges identified (Section 4.2) and responses to our interview (Section 4.3), we engaged in a user-centered iterative design process [16] to develop S IBYL , an ML augmentation tool.”
MethodInfluential
Research works printed but not linked: 8
- lipton, 2016, The Mythos of Model Interpretability, 2016 ICML Workshop on Human Interpretability in Machine Learning, 16, 31
- richardson, 1990, The Effects of a False Allegation of Child Sexual Abuse on an Intact Middle Class Family, IPT, 2, 226
- 2020, Machine Learning Glossary Fairness
- hurley, 2018, Can an Algorithm Tell When Kids Are in Danger?, 30
- kenton, 2021, How Cost-Benefit Analysis Process Is Performed, Investope-dia
- 2020, Children's Bureau, Child Maltreatment 2018 Summary of Key Findings
- vaithianathan, 2017, Developing Predictive Models to Support Child Maltreatment Hotline Screening Decisions Allegheny County Methodology and Implementation, 60
- vaithianathan, 2019, Implementing a Child Welfare Decision Aide in Douglas County
Cited by
What is Human-Centered about Human-Centered AI? A Map of the Research Landscape
Capel, T., & Brereton, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580959 · Cited by 228
“HCI methods were used in contexts to support state organ-isations to make decisions about individuals e.g., child welfare [61, 62, 277, 326], and policing and recidivism [116, 262].”
BackgroundMethodInfluentialGomez, 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
“We then analyzed the application domains where these interactions were studied.”
Nasarian, E., Alizadehsani, R., Acharya, U. R., & Tsui, K.-L. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102412 · Cited by 207
Recent Applications of Explainable AI (XAI): A Systematic Literature Review
Saarela, M., & Podgorelec, V. (2024) · Applied Sciences · doi:10.3390/app14198884 · Cited by 183
Kawakami, A., Sivaraman, V., Cheng, H.-F., Stapleton, L., Cheng, Y., Qing, D., Perer, A., Wu, Z. S., Zhu, H., & Holstein, K. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517439 · Cited by 143
Metadata
- Authors
- Zytek, A., Liu, D., Vaithianathan, R., & Veeramachaneni, K.
- Affiliations
- Massachusetts Institute of Technology (US)
- Auckland University of Technology (NZ)
- Venue
- IEEE Transactions on Visualization and Computer Graphics
- Published
- 2022-01
- Volume
- 28
- Issue
- 1
- Pages
- 1161-1171
- ISSN
- 1077-2626 (ISSN-L)
- 1941-0506
- 2160-9306
- OpenAlex
- W3199145056
- Cited by
- 62
- References
- 21
- Citations by year
- 2026: 7 · 2025: 22 · 2024: 15 · 2023: 10 · 2022: 8
- FWCI
- 2.92
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Visualization and Computer Graphics (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- NSF (1761812)
- 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
- high-stakes decision making, explainable machine learning, visual analytics, interpretability, trust in predictions, non-expert users, Sibyl, design implications
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: Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making. https://app.cochat.ai/papers/10.1109/tvcg.2021.3114864
- The paper
- Zytek, A., Liu, D., Vaithianathan, R., & Veeramachaneni, K. (2022). Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making. IEEE Transactions on Visualization and Computer Graphics. https://doi.org/10.1109/tvcg.2021.3114864
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.