# Saliency Learning: Teaching the Model Where to Pay Attention

arXiv: https://arxiv.org/abs/1902.08649 · HTML: https://mlsanity.com/paper/1902.08649/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2019.

## Built on by (most cited first, 23 of 23)

- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- [Leveraging Explanations in Interactive Machine Learning: An Overview](https://mlsanity.com/paper/2207.14526/) (2022)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Towards Robust Classification Model by Counterfactual and Invariant Data Generation](https://mlsanity.com/paper/2106.01127/) (2021)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [Exploring Distantly-Labeled Rationales in Neural Network Models](https://mlsanity.com/paper/2106.01809/) (2021)
- [XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models](https://mlsanity.com/paper/2210.16978/) (2022)
- [Interpretability-Aware Vision Transformer](https://mlsanity.com/paper/2309.08035/) (2023)
- [SMOOT: Saliency Guided Mask Optimized Online Training](https://mlsanity.com/paper/2310.00772/) (2023)
- [Diagnostics-Guided Explanation Generation](https://mlsanity.com/paper/2109.03756/) (2021)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales](https://mlsanity.com/paper/2404.03098/) (2024)
- [REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization](https://mlsanity.com/paper/2310.14418/) (2023)
- [SuMe: A Dataset Towards Summarizing Biomedical Mechanisms](https://mlsanity.com/paper/2205.04652/) (2022)
- [SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training](https://mlsanity.com/paper/2311.05143/) (2023)
- [CA-Stream: Attention-based pooling for interpretable image recognition](https://mlsanity.com/paper/2404.14996/) (2024)
- [The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach](https://mlsanity.com/paper/2409.17370/) (2024)
- [Explanation Regularisation through the Lens of Attributions](https://mlsanity.com/paper/2407.16693/) (2024)
- [Does Saliency-Based Training bring Robustness for Deep Neural Networks in Image Classification?](https://mlsanity.com/paper/2306.16581/) (2023)
- [Using Interpretation Methods for Model Enhancement](https://mlsanity.com/paper/2404.02068/) (2024)
- [Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment](https://mlsanity.com/paper/2506.07168/) (2025)
- [SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation](https://mlsanity.com/paper/2604.25315/) (2026)

## Abstract (arXiv)

Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches to provide insights toward the model's behaviour and predictions, which are helpful for assessing the reliability of the model's predictions. However, such methods do not improve the model's reliability. In this paper, we aim to teach the model to make the right prediction for the right reason by providing explanation training and ensuring the alignment of the model's explanation with the ground truth explanation. Our experimental results on multiple tasks and datasets demonstrate the effectiveness of the proposed method, which produces more reliable predictions while delivering better results compared to traditionally trained models.