Publication
Right for the Wrong Reasons? Evaluating Plausibility and Behavioral Change in Explanation-Guided Learning
David Dembinsky; Adriano Lucieri; Andreas Dengel
In: Proceedings of the 3rd International Conference on Explainable AI for Neural and Symbolic Methods (EXPLAINS 2026). International Conference on Explainable AI for Neural and Symbolic Methods (EXPLAINS-2026), 3rd International Conference on Explainable AI for Neural and Symbolic Methods, located at IJCCI-2026, October 28-30, Angers, France, Communications in Computer and Information Science, Springer, 2026.
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 changes and 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 explanationlevel axes. We publicly release all experimental results to enable further analysis (https://right-for-wrong-reasons.dfki.de/).