{"ID":2842347,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10439","arxiv_id":"2511.10439","title":"Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration","abstract":"Perturbation-based explanations are widely utilized to enhance the transparency of machine-learning models in practice. However, their reliability is often compromised by the unknown model behavior under the specific perturbations used. This paper investigates the relationship between uncertainty calibration - the alignment of model confidence with actual accuracy - and perturbation-based explanations. We show that models systematically produce unreliable probability estimates when subjected to explainability-specific perturbations and theoretically prove that this directly undermines global and local explanation quality. To address this, we introduce ReCalX, a novel approach to recalibrate models for improved explanations while preserving their original predictions. Empirical evaluations across diverse models and datasets demonstrate that ReCalX consistently reduces perturbation-specific miscalibration most effectively while enhancing explanation robustness and the identification of globally important input features.","short_abstract":"Perturbation-based explanations are widely utilized to enhance the transparency of machine-learning models in practice. However, their reliability is often compromised by the unknown model behavior under the specific perturbations used. This paper investigates the relationship between uncertainty calibration - the alig...","url_abs":"https://arxiv.org/abs/2511.10439","url_pdf":"https://arxiv.org/pdf/2511.10439v1","authors":"[\"Thomas Decker\",\"Volker Tresp\",\"Florian Buettner\"]","published":"2025-11-13T16:04:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}