# From Attribution to Action: Jointly ALIGNing Predictions and Explanations

arXiv: https://arxiv.org/abs/2511.06944 · HTML: https://mlsanity.com/paper/2511.06944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step](https://mlsanity.com/paper/2306.14050/) (2023)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Explanations from Large Language Models Make Small Reasoners Better](https://mlsanity.com/paper/2210.06726/) (2022)
- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment](https://mlsanity.com/paper/2202.02838/) (2022)
- [GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-ray Classification](https://mlsanity.com/paper/2305.18221/) (2023)
- [RES: A Robust Framework for Guiding Visual Explanation](https://mlsanity.com/paper/2206.13413/) (2022)
- [Are Data-driven Explanations Robust against Out-of-distribution Data?](https://mlsanity.com/paper/2303.16390/) (2023)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [SMOOT: Saliency Guided Mask Optimized Online Training](https://mlsanity.com/paper/2310.00772/) (2023)
- [Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach](https://mlsanity.com/paper/2405.06278/) (2024)
- [The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach](https://mlsanity.com/paper/2409.17370/) (2024)

## Abstract (arXiv)

Explanation-guided learning (EGL) has shown promise in aligning model predictions with interpretable reasoning, particularly in computer vision tasks. However, most approaches rely on external annotations or heuristic-based segmentation to supervise model explanations, which can be noisy, imprecise and difficult to scale. In this work, we provide both empirical and theoretical evidence that low-quality supervision signals can degrade model performance rather than improve it. In response, we propose ALIGN, a novel framework that jointly trains a classifier and a masker in an iterative manner. The masker learns to produce soft, task-relevant masks that highlight informative regions, while the classifier is optimized for both prediction accuracy and alignment between its saliency maps and the learned masks. By leveraging high-quality masks as guidance, ALIGN improves both interpretability and generalizability, showing its superiority across various settings. Experiments on the two domain generalization benchmarks, VLCS and Terra Incognita, show that ALIGN consistently outperforms six strong baselines in both in-distribution and out-of-distribution settings. Besides, ALIGN also yields superior explanation quality concerning sufficiency and comprehensiveness, highlighting its effectiveness in producing accurate and interpretable models.