{"list":"other","total":57,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"1901.09392","title":"On the (In)fidelity and Sensitivity for Explanations","created":"2019-01-27","cited_by_count":310},{"id":"1605.01713","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","created":"2016-05-05","cited_by_count":297},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"1711.09404","title":"Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients","created":"2017-11-26","cited_by_count":236},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2009.13295","title":"A Diagnostic Study of Explainability Techniques for Text Classification","created":"2020-09-25","cited_by_count":159},{"id":"1909.13584","title":"Interpretations are useful: penalizing explanations to align neural networks with prior knowledge","created":"2019-09-30","cited_by_count":145},{"id":"2005.00115","title":"Learning to Faithfully Rationalize by Construction","created":"2020-04-30","cited_by_count":113},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"1910.03065","title":"Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations","created":"2019-10-07","cited_by_count":71},{"id":"1906.08286","title":"Incorporating Priors with Feature Attribution on Text Classification","created":"2019-06-19","cited_by_count":68},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66},{"id":"1507.00677","title":"Distributional Smoothing with Virtual Adversarial Training","created":"2015-07-02","cited_by_count":61},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59},{"id":"1611.07270","title":"Investigating the influence of noise and distractors on the interpretation of neural networks","created":"2016-11-22","cited_by_count":54},{"id":"2006.00442","title":"Evaluations and Methods for Explanation through Robustness Analysis","created":"2020-05-31","cited_by_count":51},{"id":"1910.02065","title":"Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods","created":"2019-10-04","cited_by_count":38},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31},{"id":"2108.04990","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","created":"2021-08-11","cited_by_count":30},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21},{"id":"2203.00056","title":"An Empirical Study on Explanations in Out-of-Domain Settings","created":"2022-02-28","cited_by_count":21},{"id":"2110.07586","title":"Can Explanations Be Useful for Calibrating Black Box Models?","created":"2021-10-14","cited_by_count":20},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16},{"id":"2109.08259","title":"Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU","created":"2021-09-17","cited_by_count":13},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13},{"id":"2112.10424","title":"Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction","created":"2021-12-20","cited_by_count":11},{"id":"1809.10804","title":"Patient Risk Assessment and Warning Symptom Detection Using Deep Attention-Based Neural Networks","created":"2018-09-28","cited_by_count":7},{"id":"2212.05327","title":"Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification","created":"2022-12-10","cited_by_count":2}],"next_cursor":null}