mlsanityData to 7 Oct 2026

"Trust Junk" Leads to Unjustified Support for Highly Discriminatory Predictive Models

arXiv 2607.14152 ↗First posted 14 Jul 2026cs.HC cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The persuasive power of data visualizations can go awry: for instance, in an explainable AI (XAI) context, visualizations can produce over-trust of predictive models. In this paper, we use a crowdsourced study to show that providing accurate (but superfluous or irrelevant) data in a model explanation can, in fact, result in unjustified trust and other positive beliefs about a model, even when the model is patently discriminatory and unfair. Our results suggest that XAI designers and developers need to consider the implicit or explicit rhetorics of their work, and beware of the potential of visualizations to imbue models with unearned trust.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 42 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

19 of 42 references.

References · 19

  1. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  2. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  3. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  4. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
  5. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  6. 2019"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanationscited by 111
  7. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  8. 2019Fairwashing: the risk of rationalizationcited by 81
  9. 2021Explainability Pitfalls: Beyond Dark Patterns in Explainable AIcited by 36
  10. 2023Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAIcited by 33
  11. 2021"Look! It's a Computer Program! It's an Algorithm! It's AI!": Does Terminology Affect Human Perceptions and Evaluations of Algorithmic Decision-Making Systems?cited by 13
  12. 2020Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognitioncited by 11
7 more
  1. 2017Transparency: Motivations and Challengescited by 10
  2. 2022The Algorithmic Imprintcited by 10
  3. 2019Illusion of Causality in Visualized Datacited by 8
  4. 2021AdViCE: Aggregated Visual Counterfactual Explanations for Machine Learning Model Validationcited by 7
  5. 2019Data is Personal: Attitudes and Perceptions of Data Visualization in Rural Pennsylvaniacited by 4
  6. 2023The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Featurescited by 3
  7. 2021Towards a Theory of Bullshit Visualizationcited by 1

Built on by

Not cited yet.