# Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations

arXiv: https://arxiv.org/abs/2101.09498 · HTML: https://mlsanity.com/paper/2101.09498/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 87 references that are in the map.
- First posted on arXiv 23 Jan 2021.

## Builds on (most cited first, 22 of 22)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making](https://mlsanity.com/paper/1902.02960/) (2019)
- ["Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans](https://mlsanity.com/paper/2001.05871/) (2020)
- [Beyond Sparsity: Tree Regularization of Deep Models for Interpretability](https://mlsanity.com/paper/1711.06178/) (2017)
- [DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems](https://mlsanity.com/paper/1906.10263/) (2019)
- [Robust Attribution Regularization](https://mlsanity.com/paper/1905.09957/) (2019)
- [Improving performance of deep learning models with axiomatic attribution priors and expected gradients](https://mlsanity.com/paper/1906.10670/) (2019)
- [Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience](https://mlsanity.com/paper/2001.09219/) (2020)
- [Do Not Trust Additive Explanations](https://mlsanity.com/paper/1903.11420/) (2019)
- [Attributional Robustness Training using Input-Gradient Spatial Alignment](https://mlsanity.com/paper/1911.13073/) (2019)
- [On The Stability of Interpretable Models](https://mlsanity.com/paper/1810.09352/) (2018)

## Built on by (most cited first, 15 of 15)

- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Towards Relatable Explainable AI with the Perceptual Process](https://mlsanity.com/paper/2112.14005/) (2021)
- [Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions](https://mlsanity.com/paper/2302.07248/) (2023)
- [Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation](https://mlsanity.com/paper/2109.10149/) (2021)
- [Incremental XAI: Memorable Understanding of AI with Incremental Explanations](https://mlsanity.com/paper/2404.06733/) (2024)
- [Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidence](https://mlsanity.com/paper/2206.02790/) (2022)
- [Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis](https://mlsanity.com/paper/2302.01241/) (2023)
- [Explaining Model Confidence Using Counterfactuals](https://mlsanity.com/paper/2303.05729/) (2023)
- [Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input](https://mlsanity.com/paper/2312.06797/) (2023)
- [When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making](https://mlsanity.com/paper/2602.04003/) (2026)
- [REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability](https://mlsanity.com/paper/2412.08513/) (2024)
- [Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust](https://mlsanity.com/paper/2508.07095/) (2025)
- [Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learning](https://mlsanity.com/paper/2201.12835/) (2022)
- [Your Model Is Unfair, Are You Even Aware? Inverse Relationship Between Comprehension and Trust in Explainability Visualizations of Biased ML Models](https://mlsanity.com/paper/2508.00140/) (2025)
- [Trust in foundation models and GenAI: A geographic perspective](https://mlsanity.com/paper/2510.17942/) (2025)

## Abstract (arXiv)

Feature attribution is widely used in interpretable machine learning to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the awareness of input uncertainty can affect the trust in explanations. We propose and study two approaches to help users to manage their perception of uncertainty in a model explanation: 1) transparently show uncertainty in feature attributions to allow users to reflect on, and 2) suppress attribution to features with uncertain measurements and shift attribution to other features by regularizing with an uncertainty penalty. Through simulation experiments, qualitative interviews, and quantitative user evaluations, we identified the benefits of moderately suppressing attribution uncertainty, and concerns regarding showing attribution uncertainty. This work adds to the understanding of handling and communicating uncertainty for model interpretability.