{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"1812.05271","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","created":"2018-12-13","cited_by_count":381},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"1801.04354","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","created":"2018-01-13","cited_by_count":345},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"1801.02610","title":"Generating Adversarial Examples with Adversarial Networks","created":"2018-01-08","cited_by_count":258},{"id":"1710.04806","title":"Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions","created":"2017-10-13","cited_by_count":234},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232},{"id":"2012.02046","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","created":"2020-12-03","cited_by_count":214},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211},{"id":"1803.04765","title":"Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning","created":"2018-03-13","cited_by_count":207},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"1805.03438","title":"Robust Classification with Convolutional Prototype Learning","created":"2018-05-09","cited_by_count":123},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"2004.08994","title":"Adversarial Training for Large Neural Language Models","created":"2020-04-20","cited_by_count":111},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"2108.12237","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","created":"2021-08-27","cited_by_count":87},{"id":"1901.10514","title":"Hyperspherical Prototype Networks","created":"2019-01-29","cited_by_count":86},{"id":"2004.14174","title":"Reevaluating Adversarial Examples in Natural Language","created":"2020-04-25","cited_by_count":85},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73},{"id":"1907.09728","title":"Interpretable and Steerable Sequence Learning via Prototypes","created":"2019-07-23","cited_by_count":72},{"id":"1906.10651","title":"Interpretable Image Recognition with Hierarchical Prototypes","created":"2019-06-25","cited_by_count":65},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65},{"id":"1912.02523","title":"Towards Explainable Deep Neural Networks (xDNN)","created":"2019-12-05","cited_by_count":61},{"id":"2010.02458","title":"Identifying Spurious Correlations for Robust Text Classification","created":"2020-10-06","cited_by_count":59},{"id":"2011.02863","title":"This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition","created":"2020-11-05","cited_by_count":50},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50},{"id":"2011.08899","title":"Multimodal Prototypical Networks for Few-shot Learning","created":"2020-11-17","cited_by_count":48},{"id":"2012.15699","title":"Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning","created":"2020-12-31","cited_by_count":39},{"id":"1812.00151","title":"Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification","created":"2018-12-01","cited_by_count":35},{"id":"2005.00782","title":"RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms","created":"2020-05-02","cited_by_count":28},{"id":"2109.05473","title":"Exploring Task Difficulty for Few-Shot Relation Extraction","created":"2021-09-12","cited_by_count":24},{"id":"2009.06368","title":"Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples","created":"2020-09-09","cited_by_count":23},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21},{"id":"1905.07186","title":"How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twins","created":"2019-05-17","cited_by_count":20},{"id":"2006.16336","title":"Learning Sparse Prototypes for Text Generation","created":"2020-06-29","cited_by_count":15},{"id":"2212.07425","title":"Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments","created":"2022-12-12","cited_by_count":12},{"id":"2310.06966","title":"On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis","created":"2023-10-10","cited_by_count":11},{"id":"2310.15743","title":"RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction","created":"2023-10-24","cited_by_count":9},{"id":"2104.11103","title":"Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions","created":"2021-04-22","cited_by_count":7},{"id":"2210.08500","title":"This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text","created":"2022-10-16","cited_by_count":6},{"id":"2207.07208","title":"Provably Adversarially Robust Nearest Prototype Classifiers","created":"2022-07-14","cited_by_count":2}],"next_cursor":null}