{"list":"other","total":69,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1712.05055","title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","created":"2017-12-14","cited_by_count":653},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"1805.12185","title":"Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks","created":"2018-05-30","cited_by_count":580},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1908.06112","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","created":"2019-08-16","cited_by_count":500},{"id":"1901.04215","title":"How does Disagreement Help Generalization against Label Corruption?","created":"2019-01-14","cited_by_count":390},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"1904.11238","title":"Unsupervised Label Noise Modeling and Loss Correction","created":"2019-04-25","cited_by_count":328},{"id":"2101.05930","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","created":"2021-01-15","cited_by_count":324},{"id":"1412.6596","title":"Training Deep Neural Networks on Noisy Labels with Bootstrapping","created":"2014-12-20","cited_by_count":322},{"id":"1912.02771","title":"Label-Consistent Backdoor Attacks","created":"2019-12-05","cited_by_count":296},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"2003.02752","title":"Combating noisy labels by agreement: A joint training method with co-regularization","created":"2020-03-05","cited_by_count":289},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"1902.09666","title":"Predicting the Type and Target of Offensive Posts in Social Media","created":"2019-02-25","cited_by_count":271},{"id":"2011.10369","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","created":"2020-11-20","cited_by_count":263},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263},{"id":"1905.12457","title":"A backdoor attack against LSTM-based text classification systems","created":"2019-05-29","cited_by_count":227},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222},{"id":"2006.01043","title":"BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements","created":"2020-06-01","cited_by_count":211},{"id":"2003.02819","title":"Does label smoothing mitigate label noise?","created":"2020-03-05","cited_by_count":204},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202},{"id":"1910.01842","title":"SELF: Learning to Filter Noisy Labels with Self-Ensembling","created":"2019-10-04","cited_by_count":164},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158},{"id":"1909.06321","title":"End-to-End Bias Mitigation by Modelling Biases in Corpora","created":"2019-09-13","cited_by_count":128},{"id":"1908.10763","title":"Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual","created":"2019-08-28","cited_by_count":119},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"2106.15853","title":"Understanding and Improving Early Stopping for Learning with Noisy Labels","created":"2021-06-30","cited_by_count":113},{"id":"2108.13888","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","created":"2021-08-31","cited_by_count":113},{"id":"2203.04181","title":"Selective-Supervised Contrastive Learning with Noisy Labels","created":"2022-03-08","cited_by_count":112},{"id":"2103.15543","title":"Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models","created":"2021-03-29","cited_by_count":105},{"id":"2110.07831","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","created":"2021-10-15","cited_by_count":104},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91},{"id":"2008.00312","title":"Trojaning Language Models for Fun and Profit","created":"2020-08-01","cited_by_count":90},{"id":"2105.10123","title":"Backdoor Attacks on Self-Supervised Learning","created":"2021-05-21","cited_by_count":90},{"id":"2106.06361","title":"Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution","created":"2021-06-11","cited_by_count":89},{"id":"2007.12070","title":"Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification","created":"2020-07-11","cited_by_count":86},{"id":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"2012.05458","title":"Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise","created":"2020-12-10","cited_by_count":82},{"id":"2106.00445","title":"Sample Selection with Uncertainty of Losses for Learning with Noisy Labels","created":"2021-06-01","cited_by_count":79},{"id":"2011.10077","title":"Error-Bounded Correction of Noisy Labels","created":"2020-11-19","cited_by_count":74},{"id":"2206.08514","title":"A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks","created":"2022-06-17","cited_by_count":74},{"id":"1911.10312","title":"Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks","created":"2019-11-23","cited_by_count":71},{"id":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66},{"id":"2103.04264","title":"T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification","created":"2021-03-07","cited_by_count":60},{"id":"2010.02458","title":"Identifying Spurious Correlations for Robust Text Classification","created":"2020-10-06","cited_by_count":59},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53},{"id":"2205.08305","title":"A Study of the Attention Abnormality in Trojaned BERTs","created":"2022-05-13","cited_by_count":48},{"id":"2011.03856","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles","created":"2020-11-07","cited_by_count":43},{"id":"2212.09067","title":"Fine-Tuning Is All You Need to Mitigate Backdoor Attacks","created":"2022-12-18","cited_by_count":38},{"id":"2303.06818","title":"Backdoor Defense via Deconfounded Representation Learning","created":"2023-03-13","cited_by_count":38},{"id":"2104.08656","title":"Learning from Noisy Labels for Entity-Centric Information Extraction","created":"2021-04-17","cited_by_count":34},{"id":"2109.02071","title":"End-to-End Self-Debiasing Framework for Robust NLU Training","created":"2021-09-05","cited_by_count":24},{"id":"2109.10855","title":"BFClass: A Backdoor-free Text Classification Framework","created":"2021-09-22","cited_by_count":19},{"id":"2211.12044","title":"Backdoor Cleansing with Unlabeled Data","created":"2022-11-22","cited_by_count":17},{"id":"2205.11803","title":"WeDef: Weakly Supervised Backdoor Defense for Text Classification","created":"2022-05-24","cited_by_count":15},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10},{"id":"2012.05273","title":"MetaInfoNet: Learning Task-Guided Information for Sample Reweighting","created":"2020-12-09","cited_by_count":5}],"next_cursor":null}