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

arXiv: https://arxiv.org/abs/2607.14152 · HTML: https://mlsanity.com/paper/2607.14152/

## Key facts

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

## Builds on (most cited first, 19 of 19)

- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Questioning the AI: Informing Design Practices for Explainable AI User Experiences](https://mlsanity.com/paper/2001.02478/) (2020)
- [Learning to Deceive with Attention-Based Explanations](https://mlsanity.com/paper/1909.07913/) (2019)
- ["How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations](https://mlsanity.com/paper/1911.06473/) (2019)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [Fairwashing: the risk of rationalization](https://mlsanity.com/paper/1901.09749/) (2019)
- [Explainability Pitfalls: Beyond Dark Patterns in Explainable AI](https://mlsanity.com/paper/2109.12480/) (2021)
- [Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI](https://mlsanity.com/paper/2302.00799/) (2023)
- ["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?](https://mlsanity.com/paper/2108.11486/) (2021)
- [Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition](https://mlsanity.com/paper/2005.02335/) (2020)
- [Transparency: Motivations and Challenges](https://mlsanity.com/paper/1708.01870/) (2017)
- [The Algorithmic Imprint](https://mlsanity.com/paper/2206.03275/) (2022)
- [Illusion of Causality in Visualized Data](https://mlsanity.com/paper/1908.00215/) (2019)
- [AdViCE: Aggregated Visual Counterfactual Explanations for Machine Learning Model Validation](https://mlsanity.com/paper/2109.05629/) (2021)
- [Data is Personal: Attitudes and Perceptions of Data Visualization in Rural Pennsylvania](https://mlsanity.com/paper/1901.01920/) (2019)
- [The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features](https://mlsanity.com/paper/2310.08617/) (2023)
- [Towards a Theory of Bullshit Visualization](https://mlsanity.com/paper/2109.12975/) (2021)

## 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.