cs.LGNov 10, 2026

Right for the Wrong Reasons? Evaluating Plausibility and Behavioral Change in Explanation-Guided Learning

Authors: David Dembinsky, Adriano Lucieri, Andreas Dengel

Organizations: German Research Center for Artificial Intelligence (DFKI) GmbH, Germany · RPTU University Kaiserslautern-Landau, Germany

Abstract

Explanation-Guided Learning (EGL) promises models that are not only accurate but also rely on task-relevant evidence. However, whether improved agreement between model explanations and human-provided rationales also implies a changed decision strategy remains unclear. We study this tension under controlled synthetic shortcut introduction using a constructed shortcut dataset. Inspired by real-world applications, our benchmark covers shortcuts of different kinds, including localized, background-based, and global cues. This allows us to evaluate whether different EGL objectives produce behavioral changesand explanatory changes. Across these axes, we find that the effects of EGL are strongly objective-specific. Rationale-based data augmentation provides the clearest robustness gains when shortcut evidence can be separated from task-relevant foreground information, reaching average accuracy improvements of up to +4.8 percentage points (pp) together with increased foreground reliance. Attribution-constraining objectives primarily improve explanation plausibility, increasing Importance Mass by up to +14 pp on average, but provide weaker and less consistent behavioral correction, with average accuracy gains of at most +1.6 pp. Moreover, neither improved robustness nor improved plausibility reliably implies higher perturbation-based fidelity. Overall, our results show that EGL can be useful, but its success cannot be inferred from rationale agreement alone and should instead be evaluated along complementary behavioral and explanation-level axes. We publicly release all experimental results to enable further analysis (https://right-for-wrong-reasons.dfki.de/).

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Explanation-Guided Adversarial Training for Robust and Interpretable Models

    Mar 2, 2026Chao Chen, Yanhui Chen, Shanshan Lin +4Adversarial TrainingAdversarial Robustness

  2. Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations

    Mar 16, 2026Sumedha Chugh, Ranjitha Prasad, Nazreen ShahPerturbation-Based Feature AttributionUncertainty Quantification