{"list":"other","total":104,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"1710.10571","title":"Certifying Some Distributional Robustness with Principled Adversarial Training","created":"2017-10-29","cited_by_count":337},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"1812.03411","title":"Feature Denoising for Improving Adversarial Robustness","created":"2018-12-09","cited_by_count":314},{"id":"1912.05511","title":"Measurement and Fairness","created":"2019-12-11","cited_by_count":308},{"id":"1802.00393","title":"Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior","created":"2018-02-01","cited_by_count":270},{"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":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234},{"id":"1711.06664","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer","created":"2017-11-17","cited_by_count":233},{"id":"2012.15606","title":"HateCheck: Functional Tests for Hate Speech Detection Models","created":"2020-12-31","cited_by_count":216},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"1906.06316","title":"Towards Stable and Efficient Training of Verifiably Robust Neural Networks","created":"2019-06-14","cited_by_count":205},{"id":"2111.05328","title":"Data Augmentation Can Improve Robustness","created":"2021-11-09","cited_by_count":194},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186},{"id":"1801.10578","title":"Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach","created":"2018-01-31","cited_by_count":182},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"1812.10528","title":"Adversarial Attack and Defense on Graph Data: A Survey","created":"2018-12-26","cited_by_count":167},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138},{"id":"2007.06778","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","created":"2020-07-14","cited_by_count":134},{"id":"1903.03425","title":"The Ethics of AI Ethics -- An Evaluation of Guidelines","created":"2019-02-28","cited_by_count":129},{"id":"2104.09425","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","created":"2021-04-19","cited_by_count":113},{"id":"2003.05161","title":"A Benchmark for Systematic Generalization in Grounded Language Understanding","created":"2020-03-11","cited_by_count":108},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"1803.01128","title":"Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples","created":"2018-03-03","cited_by_count":94},{"id":"1811.11154","title":"Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved","created":"2018-11-27","cited_by_count":94},{"id":"2010.02329","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","created":"2020-10-05","cited_by_count":92},{"id":"1803.08680","title":"Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization","created":"2018-03-23","cited_by_count":88},{"id":"2004.11999","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","created":"2020-04-24","cited_by_count":86},{"id":"2107.03721","title":"Demystifying the Draft EU Artificial Intelligence Act","created":"2021-07-08","cited_by_count":84},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79},{"id":"2002.09343","title":"Robust Optimization for Fairness with Noisy Protected Groups","created":"2020-02-21","cited_by_count":78},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76},{"id":"1810.09619","title":"Sparse DNNs with Improved Adversarial Robustness","created":"2018-10-23","cited_by_count":72},{"id":"2002.06789","title":"CAT: Customized Adversarial Training for Improved Robustness","created":"2020-02-17","cited_by_count":61},{"id":"1909.00066","title":"Counterfactual Risk Assessments, Evaluation, and Fairness","created":"2019-08-30","cited_by_count":59},{"id":"1807.00028","title":"Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints","created":"2018-06-29","cited_by_count":53},{"id":"1902.01509","title":"Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation","created":"2019-02-05","cited_by_count":52},{"id":"1906.09218","title":"FlipTest: Fairness Testing via Optimal Transport","created":"2019-06-21","cited_by_count":51},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50},{"id":"2110.14222","title":"Sample Selection for Fair and Robust Training","created":"2021-10-27","cited_by_count":48},{"id":"1910.12908","title":"Certified Adversarial Robustness for Deep Reinforcement Learning","created":"2019-10-28","cited_by_count":47},{"id":"2112.07610","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","created":"2021-12-14","cited_by_count":46},{"id":"1804.06473","title":"Robust Machine Comprehension Models via Adversarial Training","created":"2018-04-17","cited_by_count":44},{"id":"2007.02924","title":"INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving","created":"2020-07-06","cited_by_count":44},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43},{"id":"1904.02668","title":"Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets","created":"2019-04-04","cited_by_count":42},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41},{"id":"2009.02841","title":"Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Odds","created":"2020-09-07","cited_by_count":40},{"id":"2110.05367","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","created":"2021-10-11","cited_by_count":35},{"id":"2012.04800","title":"A Statistical Test for Probabilistic Fairness","created":"2020-12-09","cited_by_count":25},{"id":"2204.07932","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","created":"2022-04-17","cited_by_count":21},{"id":"2002.05193","title":"A Hierarchy of Limitations in Machine Learning","created":"2020-02-12","cited_by_count":20},{"id":"2303.00442","title":"Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization","created":"2023-03-01","cited_by_count":20},{"id":"2109.11196","title":"Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold","created":"2021-09-23","cited_by_count":18},{"id":"2202.01906","title":"Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcare","created":"2022-02-03","cited_by_count":16},{"id":"2205.08704","title":"Accurate Fairness: Improving Individual Fairness without Trading Accuracy","created":"2022-05-18","cited_by_count":16},{"id":"2203.02006","title":"Why adversarial training can hurt robust accuracy","created":"2022-03-03","cited_by_count":14},{"id":"2206.02792","title":"FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data","created":"2022-06-06","cited_by_count":13}],"next_cursor":"100"}