3 papers
cs.CL2026
Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids
Fabian Lukassen, Jan Herrmann, Christoph Weisser +3
Prior work shows that Large Language Models (LLMs) can transform Explainable AI (XAI) outputs into Natural Language Explanations (NLEs) that score highly on quality metrics such as…
cs.LG2025
Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples
Sidney Bender, Ole Delzer, Jan Herrmann +3
Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-super…
cs.LG2025
Towards Desiderata-Driven Design of Visual Counterfactual Explainers
Sidney Bender, Jan Herrmann, Klaus-Robert Müller +1
Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations…