mlsanityData to 7 Oct 2026

Getting a CLUE: A Method for Explaining Uncertainty Estimates

arXiv 2006.06848 ↗First posted 11 Jun 2020stat.ML cs.LGcited by 92

Not on the map. Why?

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.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 17; 2023: 18; 2024: 18; 2025: 15; 2026: 9.

92 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  3. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  4. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  5. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  6. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  7. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  8. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
  9. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  10. 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
  11. 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
  12. 2022On the Privacy Risks of Algorithmic Recoursecited by 32
38 more
  1. 2022Adapting the Linearised Laplace Model Evidence for Modern Deep Learningcited by 29
  2. 2022On the Trade-Off between Actionable Explanations and the Right to be Forgottencited by 20
  3. 2021Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimatescited by 19
  4. 2023Calibrated Explanations: with Uncertainty Information and Counterfactualscited by 16
  5. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  6. 2023Learning Personalized Decision Support Policiescited by 13
  7. 2021RELAX: Representation Learning Explainabilitycited by 12
  8. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  9. 2022Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Priorcited by 10
  10. 2023Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspectivecited by 10
  11. 2022Provable concept learning for interpretable predictions using variational autoencoderscited by 9
  12. 2023Endogenous Macrodynamics in Algorithmic Recoursecited by 9
  13. 2024Explaining Predictive Uncertainty by Exposing Second-Order Effectscited by 9
  14. 2024A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learningcited by 9
  15. 2024Counterfactual Explanations via Riemannian Latent Space Traversalcited by 9
  16. 2021Attribution of Predictive Uncertainties in Classification Modelscited by 8
  17. 2023Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learningcited by 8
  18. 2024TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAEcited by 8
  19. 2021Shapley variable importance clouds for interpretable machine learningcited by 7
  20. 2021MCCE: Monte Carlo sampling of realistic counterfactual explanationscited by 7
  21. 2022Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Priorcited by 7
  22. 2021Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approachcited by 6
  23. 2023Model-agnostic variable importance for predictive uncertainty: an entropy-based approachcited by 6
  24. 2021To Trust or Not to Trust a Regressor: Estimating and Explaining Trustworthiness of Regression Predictionscited by 5
  25. 2024"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shiftscited by 5
  26. 2025From Search To Sampling: Generative Models For Robust Algorithmic Recoursecited by 5
  27. 2021δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimatescited by 4
  28. 2022Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidencecited by 4
  29. 2022Computing Rule-Based Explanations by Leveraging Counterfactualscited by 4
  30. 2023Explaining Model Confidence Using Counterfactualscited by 4
  31. 2023Explaining Black-Box Models through Counterfactualscited by 4
  32. 2023Identifying Drivers of Predictive Aleatoric Uncertaintycited by 4
  33. 2024QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanationscited by 4
  34. 2024Generating Feasible and Plausible Counterfactual Explanations for Outcome Prediction of Business Processescited by 4
  35. 2024Enhancing Counterfactual Explanation Search with Diffusion Distance and Directional Coherencecited by 4
  36. 2024X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Imagescited by 4
  37. 2025Trustworthy AI Must Account for Interactionscited by 4
  38. 2025Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervalscited by 4

50 most cited of 92 All 92 (JSON)