2025 "explanation robustness" Papers
2 papers found
Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
Thomas Decker, Volker Tresp, Florian Buettner
NEURIPS 2025spotlightarXiv:2511.10439
Probabilistic Stability Guarantees for Feature Attributions
Helen Jin, Anton Xue, Weiqiu You et al.
NEURIPS 2025posterarXiv:2504.13787
6
citations