# δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates

arXiv: https://arxiv.org/abs/2104.06323 · HTML: https://mlsanity.com/paper/2104.06323/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 8 of 8)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [Efficient Search for Diverse Coherent Explanations](https://mlsanity.com/paper/1901.04909/) (2019)
- [Getting a CLUE: A Method for Explaining Uncertainty Estimates](https://mlsanity.com/paper/2006.06848/) (2020)
- [Variational Autoencoder with Arbitrary Conditioning](https://mlsanity.com/paper/1806.02382/) (2018)
- [xGEMs: Generating Examplars to Explain Black-Box Models](https://mlsanity.com/paper/1806.08867/) (2018)
- [MNIST Dataset Classification Utilizing k-NN Classifier with Modified Sliding-window Metric](https://mlsanity.com/paper/1809.06846/) (2018)

## Built on by (most cited first, 4 of 4)

- [Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates](https://mlsanity.com/paper/2112.02646/) (2021)
- [Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning](https://mlsanity.com/paper/2304.04824/) (2023)
- [When Explanations Compete: Policy-Aware Selection Under Uncertainty](https://mlsanity.com/paper/2410.05479/) (2024)
- [Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantification](https://mlsanity.com/paper/2504.02606/) (2025)

## Abstract (arXiv)

To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating Counterfactual Latent Uncertainty Explanations (CLUEs). However, for a single input, such approaches could output a variety of explanations due to the lack of constraints placed on the explanation. Here we augment the original CLUE approach, to provide what we call δ-CLUE. CLUE indicates itone way to change an input, while remaining on the data manifold, such that the model becomes more confident about its prediction. We instead return a itset of plausible CLUEs: multiple, diverse inputs that are within a δ ball of the original input in latent space, all yielding confident predictions.