Work

Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators

Year: 2025

Type: conference-paper

Abstract: Understanding uncertainty in Explainable AI (XAI) is crucial for building trust and ensuring reliable decision-making in Machine Learning models. This paper introduces a unified framework for quantifying and interpreting Uncertainty in XAI by defining a general explanation function $$e_{\theta}(x, f)$$ e θ ( x , f ) that captures the propagation of uncertainty from key sources: perturbations in input data and model parameters. By using both analytical and empirical estimates of explanation variance, we provide a systematic means of assessing the impact uncertainty on explanations. We illustrate the approach using a first-order uncertainty propagation as the analytical estimator. In a comprehensive evaluation across heterogeneous datasets, we compare analytical and empirical estimates of uncertainty propagation and evaluate their robustness. Extending previous work on inconsistencies in explanations, our experiments identify XAI methods that do not reliably capture and propagate uncertainty. Our findings underscore the importance of uncertainty-aware explanations in high-stakes applications and offer new insights into the limitations of current XAI methods. The code for the experiments can be found in our repository: https://github.com/TeodorChiaburu/UXAI .

Source: Communications in computer and information science

DOI: 10.1007/978-3-032-08333-3_18

Authors: Teodor Chiaburu, Felix Bießmann, Frank Haußer

Institutions: Berliner Hochschule für Technik, Einstein Center Digital Future

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Bundesministerium für Wirtschaft und Klimaschutz, Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung