# Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction

arXiv: https://arxiv.org/abs/2112.10424 · HTML: https://mlsanity.com/paper/2112.10424/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 20 Dec 2021.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://mlsanity.com/paper/1911.03437/) (2019)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Contextualized Perturbation for Textual Adversarial Attack](https://mlsanity.com/paper/2009.07502/) (2020)
- [Interpretable Neural Predictions with Differentiable Binary Variables](https://mlsanity.com/paper/1905.08160/) (2019)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [Adversarial Training for Large Neural Language Models](https://mlsanity.com/paper/2004.08994/) (2020)
- [On the Connection Between Adversarial Robustness and Saliency Map Interpretability](https://mlsanity.com/paper/1905.04172/) (2019)
- [Adversarial Robustness on In- and Out-Distribution Improves Explainability](https://mlsanity.com/paper/2003.09461/) (2020)
- [Joint Embedding of Words and Labels for Text Classification](https://mlsanity.com/paper/1805.04174/) (2018)
- [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://mlsanity.com/paper/2005.00652/) (2020)
- [Inferring Which Medical Treatments Work from Reports of Clinical Trials](https://mlsanity.com/paper/1904.01606/) (2019)
- [On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models](https://mlsanity.com/paper/1903.06620/) (2019)
- [Robust Machine Comprehension Models via Adversarial Training](https://mlsanity.com/paper/1804.06473/) (2018)
- [Rationale-Augmented Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/1605.04469/) (2016)

## Built on by (most cited first, 11 of 11)

- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery](https://mlsanity.com/paper/2403.07955/) (2024)
- [Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training](https://mlsanity.com/paper/2312.17591/) (2023)
- [You Only Forward Once: Prediction and Rationalization in A Single Forward Pass](https://mlsanity.com/paper/2311.02344/) (2023)
- [EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction](https://mlsanity.com/paper/2407.00924/) (2024)
- [Adversarial Attack for Explanation Robustness of Rationalization Models](https://mlsanity.com/paper/2408.10795/) (2024)
- [Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction](https://mlsanity.com/paper/2502.15261/) (2025)
- [Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization](https://mlsanity.com/paper/2510.13393/) (2025)
- [MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use](https://mlsanity.com/paper/2608.20202/) (2026)
- [Hybrid Attribution Priors for Explainable and Robust Model Training](https://mlsanity.com/paper/2512.14719/) (2025)

## Abstract (arXiv)

Recent works have shown explainability and robustness are two crucial ingredients of trustworthy and reliable text classification. However, previous works usually address one of two aspects: i) how to extract accurate rationales for explainability while being beneficial to prediction; ii) how to make the predictive model robust to different types of adversarial attacks. Intuitively, a model that produces helpful explanations should be more robust against adversarial attacks, because we cannot trust the model that outputs explanations but changes its prediction under small perturbations. To this end, we propose a joint classification and rationale extraction model named AT-BMC. It includes two key mechanisms: mixed Adversarial Training (AT) is designed to use various perturbations in discrete and embedding space to improve the model's robustness, and Boundary Match Constraint (BMC) helps to locate rationales more precisely with the guidance of boundary information. Performances on benchmark datasets demonstrate that the proposed AT-BMC outperforms baselines on both classification and rationale extraction by a large margin. Robustness analysis shows that the proposed AT-BMC decreases the attack success rate effectively by up to 69%. The empirical results indicate that there are connections between robust models and better explanations.