# Learning Credible Deep Neural Networks with Rationale Regularization

arXiv: https://arxiv.org/abs/1908.05601 · HTML: https://mlsanity.com/paper/1908.05601/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2019.

## Built on by (most cited first, 18 of 18)

- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [Data-centric AI: Perspectives and Challenges](https://mlsanity.com/paper/2301.04819/) (2023)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [Towards Robust Classification Model by Counterfactual and Invariant Data Generation](https://mlsanity.com/paper/2106.01127/) (2021)
- [Rationalization for Explainable NLP: A Survey](https://mlsanity.com/paper/2301.08912/) (2023)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales](https://mlsanity.com/paper/2404.03098/) (2024)
- [Privileged Attribution Constrained Deep Networks for Facial Expression Recognition](https://mlsanity.com/paper/2203.12905/) (2022)
- [Mitigating Algorithmic Bias with Limited Annotations](https://mlsanity.com/paper/2207.10018/) (2022)
- [Regularizing Explanations in Bayesian Convolutional Neural Networks](https://mlsanity.com/paper/2105.02653/) (2021)
- [Interpreting and improving deep-learning models with reality checks](https://mlsanity.com/paper/2108.06847/) (2021)
- [XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection](https://mlsanity.com/paper/2210.11590/) (2022)
- [Bias Mitigation Framework for Intersectional Subgroups in Neural Networks](https://mlsanity.com/paper/2212.13014/) (2022)
- [Applications of Explainable artificial intelligence in Earth system science](https://mlsanity.com/paper/2406.11882/) (2024)
- [Fair Machine Learning in Healthcare: A Review](https://mlsanity.com/paper/2206.14397/) (2022)
- [Using Interpretation Methods for Model Enhancement](https://mlsanity.com/paper/2404.02068/) (2024)
- [Machine Learning from Explanations](https://mlsanity.com/paper/2507.04788/) (2025)

## Abstract (arXiv)

Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions. It not only hampers their generalization but also makes them less likely to be trusted by end-users. In pursuit of developing more credible DNNs, in this paper we propose CREX, which encourages DNN models to focus more on evidences that actually matter for the task at hand, and to avoid overfitting to data-dependent bias and artifacts. Specifically, CREX regularizes the training process of DNNs with rationales, i.e., a subset of features highlighted by domain experts as justifications for predictions, to enforce DNNs to generate local explanations that conform with expert rationales. Even when rationales are not available, CREX still could be useful by requiring the generated explanations to be sparse. Experimental results on two text classification datasets demonstrate the increased credibility of DNNs trained with CREX. Comprehensive analysis further shows that while CREX does not always improve prediction accuracy on the held-out test set, it significantly increases DNN accuracy on new and previously unseen data beyond test set, highlighting the advantage of the increased credibility.