9 papers
Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches
Rick Wilming, Irem Ozseker, Luca Matteo Cornils +4
Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features. However, current approaches…
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
Saleh Afroogh, Syed Ishtiaque Ahmed, Petra Ahrweiler +46
This study provides a cross-disciplinary examination of Explainable Artificial Intelligence (XAI) approaches-focusing on deep neural networks (DNNs) and large language models (LLMs…
Explainable AI needs formalization
Stefan Haufe, Rick Wilming, Benedict Clark +4
The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its c…
cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context
Jörg Martin, Stefan Haufe
Explainable artificial intelligence promises to yield insights into relevant features, thereby enabling humans to examine and scrutinize machine learning models or even facilitatin…
Feature salience - not task-informativeness - drives machine learning model explanations
Benedict Clark, Marta Oliveira, Rick Wilming +1
Explainable AI (XAI) promises to provide insight into machine learning models' decision processes, where one goal is to identify failures such as shortcut learning. This promise re…
The effect of whitening on explanation performance
Benedict Clark, Stoyan Karastoyanov, Rick Wilming +1
Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a criti…