Achieving diversity in counterfactual explanations: a review and discussion

T Laugel, A Jeyasothy, MJ Lesot, C Marsala… - Proceedings of the …, 2023 - dl.acm.org
In the field of Explainable Artificial Intelligence (XAI), counterfactual examples explain to a
user the predictions of a trained decision model by indicating the modifications to be made …

Uncertainty quantification with pre-trained language models: A large-scale empirical analysis

Y Xiao, PP Liang, U Bhatt, W Neiswanger… - arXiv preprint arXiv …, 2022 - arxiv.org
Pre-trained language models (PLMs) have gained increasing popularity due to their
compelling prediction performance in diverse natural language processing (NLP) tasks …

Gradient-based uncertainty attribution for explainable bayesian deep learning

H Wang, D Joshi, S Wang, Q Ji - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Predictions made by deep learning models are prone to data perturbations, adversarial
attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to …

Explaining predictive uncertainty with information theoretic shapley values

D Watson, J O'Hara, N Tax… - Advances in Neural …, 2024 - proceedings.neurips.cc
Researchers in explainable artificial intelligence have developed numerous methods for
helping users understand the predictions of complex supervised learning models. By …

GLOBE-CE: A translation based approach for global counterfactual explanations

D Ley, S Mishra, D Magazzeni - International conference on …, 2023 - proceedings.mlr.press
Counterfactual explanations have been widely studied in explainability, with a range of
application dependent methods prominent in fairness, recourse and model understanding …

Bayesian hierarchical models for counterfactual estimation

N Raman, D Magazzeni… - … Conference on Artificial …, 2023 - proceedings.mlr.press
Counterfactual explanations utilize feature perturbations to analyze the outcome of an
original decision and recommend an actionable recourse. We argue that it is beneficial to …

Global counterfactual explanations: Investigations, implementations and improvements

D Ley, S Mishra, D Magazzeni - arXiv preprint arXiv:2204.06917, 2022 - arxiv.org
Counterfactual explanations have been widely studied in explainability, with a range of
application dependent methods emerging in fairness, recourse and model understanding …

X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images

Z Huang, Y Zhuang, Z Zhong, F Xu, G Cheng… - arXiv preprint arXiv …, 2024 - arxiv.org
SAR image simulation has attracted much attention due to its great potential to supplement
the scarce training data for deep learning algorithms. Consequently, evaluating the quality of …

Optimization-Based Uncertainty Attribution Via Learning Informative Perturbations

H Wang, BA Biswas, Q Ji - European Conference on Computer Vision, 2025 - Springer
Uncertainty attribution (UA) aims to identify key contributors to predictive uncertainty in deep
learning models. To improve the faithfulness of existing UA methods, we formulate UA as an …

Counterfactual explanation with missing values

K Kanamori, T Takagi, K Kobayashi, Y Ike - arXiv preprint arXiv …, 2023 - arxiv.org
Counterfactual Explanation (CE) is a post-hoc explanation method that provides a
perturbation for altering the prediction result of a classifier. Users can interpret the …