# Getting a CLUE: A Method for Explaining Uncertainty Estimates

arXiv: https://arxiv.org/abs/2006.06848 · HTML: https://mlsanity.com/paper/2006.06848/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 30 of 92)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis](https://mlsanity.com/paper/2210.04714/) (2022)
- [CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms](https://mlsanity.com/paper/2108.00783/) (2021)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI](https://mlsanity.com/paper/2402.00809/) (2024)
- [Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse](https://mlsanity.com/paper/2203.06768/) (2022)
- [Explaining Predictive Uncertainty with Information Theoretic Shapley Values](https://mlsanity.com/paper/2306.05724/) (2023)
- [On the Privacy Risks of Algorithmic Recourse](https://mlsanity.com/paper/2211.05427/) (2022)
- [Adapting the Linearised Laplace Model Evidence for Modern Deep Learning](https://mlsanity.com/paper/2206.08900/) (2022)
- [On the Trade-Off between Actionable Explanations and the Right to be Forgotten](https://mlsanity.com/paper/2208.14137/) (2022)
- [Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates](https://mlsanity.com/paper/2112.02646/) (2021)
- [Calibrated Explanations: with Uncertainty Information and Counterfactuals](https://mlsanity.com/paper/2305.02305/) (2023)
- [Efficient XAI Techniques: A Taxonomic Survey](https://mlsanity.com/paper/2302.03225/) (2023)
- [Learning Personalized Decision Support Policies](https://mlsanity.com/paper/2304.06701/) (2023)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [RELAX: Representation Learning Explainability](https://mlsanity.com/paper/2112.10161/) (2021)
- [Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Prior](https://mlsanity.com/paper/2203.00479/) (2022)
- [Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective](https://mlsanity.com/paper/2304.06412/) (2023)
- [Explaining Predictive Uncertainty by Exposing Second-Order Effects](https://mlsanity.com/paper/2401.17441/) (2024)
- [A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning](https://mlsanity.com/paper/2406.00332/) (2024)
- [Provable concept learning for interpretable predictions using variational autoencoders](https://mlsanity.com/paper/2204.00492/) (2022)
- [Endogenous Macrodynamics in Algorithmic Recourse](https://mlsanity.com/paper/2308.08187/) (2023)
- [Counterfactual Explanations via Riemannian Latent Space Traversal](https://mlsanity.com/paper/2411.02259/) (2024)
- [Attribution of Predictive Uncertainties in Classification Models](https://mlsanity.com/paper/2107.08756/) (2021)
- [Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning](https://mlsanity.com/paper/2304.04824/) (2023)
- [TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE](https://mlsanity.com/paper/2410.10463/) (2024)

## Abstract (arXiv)

Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two areas. We address this gap by proposing a novel method for interpreting uncertainty estimates from differentiable probabilistic models, like Bayesian Neural Networks (BNNs). Our method, Counterfactual Latent Uncertainty Explanations (CLUE), indicates how to change an input, while keeping it on the data manifold, such that a BNN becomes more confident about the input's prediction. We validate CLUE through 1) a novel framework for evaluating counterfactual explanations of uncertainty, 2) a series of ablation experiments, and 3) a user study. Our experiments show that CLUE outperforms baselines and enables practitioners to better understand which input patterns are responsible for predictive uncertainty.