{"list":"other","total":77,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"1812.10464","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","created":"2018-12-26","cited_by_count":434},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"1703.09207","title":"Fairness in Criminal Justice Risk Assessments: The State of the Art","created":"2017-03-27","cited_by_count":315},{"id":"1904.09077","title":"Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT","created":"2019-04-19","cited_by_count":301},{"id":"2004.10643","title":"Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection","created":"2020-04-22","cited_by_count":271},{"id":"1907.12009","title":"Representation Degeneration Problem in Training Natural Language Generation Models","created":"2019-07-28","cited_by_count":255},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"1907.05791","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","created":"2019-07-10","cited_by_count":223},{"id":"1908.10530","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","created":"2019-08-28","cited_by_count":204},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"1912.07840","title":"Cross-Lingual Ability of Multilingual BERT: An Empirical Study","created":"2019-12-17","cited_by_count":182},{"id":"1911.01464","title":"Emerging Cross-lingual Structure in Pretrained Language Models","created":"2019-11-04","cited_by_count":181},{"id":"1905.13289","title":"On the Accuracy of Influence Functions for Measuring Group Effects","created":"2019-05-30","cited_by_count":147},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2004.00010","title":"The Discrete Gaussian for Differential Privacy","created":"2020-03-31","cited_by_count":135},{"id":"2110.03620","title":"Hyperparameter Tuning with Renyi Differential Privacy","created":"2021-10-07","cited_by_count":104},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98},{"id":"1901.08665","title":"Fairness risk measures","created":"2019-01-24","cited_by_count":85},{"id":"2004.05160","title":"On the Language Neutrality of Pre-trained Multilingual Representations","created":"2020-04-09","cited_by_count":85},{"id":"2011.03731","title":"On the Privacy Risks of Algorithmic Fairness","created":"2020-11-07","cited_by_count":82},{"id":"1911.00418","title":"On Second-Order Group Influence Functions for Black-Box Predictions","created":"2019-11-01","cited_by_count":79},{"id":"2102.05262","title":"Input Similarity from the Neural Network Perspective","created":"2021-02-10","cited_by_count":79},{"id":"1812.02696","title":"Differentially Private Fair Learning","created":"2018-12-06","cited_by_count":76},{"id":"1811.07971","title":"Private Selection from Private Candidates","created":"2018-11-19","cited_by_count":75},{"id":"2011.11819","title":"When Machine Learning Meets Privacy: A Survey and Outlook","created":"2020-11-24","cited_by_count":68},{"id":"2010.01285","title":"Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness","created":"2020-10-03","cited_by_count":67},{"id":"2101.11109","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","created":"2021-01-26","cited_by_count":65},{"id":"2108.07344","title":"IsoScore: Measuring the Uniformity of Embedding Space Utilization","created":"2021-08-16","cited_by_count":53},{"id":"2009.05886","title":"Differentially Private Language Models Benefit from Public Pre-training","created":"2020-09-13","cited_by_count":47},{"id":"1808.10696","title":"How agents see things: On visual representations in an emergent language game","created":"2018-08-31","cited_by_count":45},{"id":"2111.04683","title":"Revisiting Methods for Finding Influential Examples","created":"2021-11-08","cited_by_count":39},{"id":"2004.06499","title":"What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models","created":"2020-04-14","cited_by_count":35},{"id":"2008.06788","title":"Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigation","created":"2020-08-15","cited_by_count":34},{"id":"1905.06401","title":"Correlating neural and symbolic representations of language","created":"2019-05-14","cited_by_count":33},{"id":"2008.02766","title":"Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging","created":"2020-08-06","cited_by_count":32},{"id":"2109.08406","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","created":"2021-09-17","cited_by_count":30},{"id":"2205.04182","title":"Enhancing Cross-lingual Transfer by Manifold Mixup","created":"2022-05-09","cited_by_count":30},{"id":"2206.09755","title":"Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold","created":"2022-06-20","cited_by_count":29},{"id":"2106.01183","title":"A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space","created":"2021-06-02","cited_by_count":27},{"id":"2109.03175","title":"When differential privacy meets NLP: The devil is in the detail","created":"2021-09-07","cited_by_count":25},{"id":"2009.12862","title":"What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties","created":"2020-09-27","cited_by_count":23},{"id":"2105.14203","title":"Understanding Instance-based Interpretability of Variational Auto-Encoders","created":"2021-05-29","cited_by_count":21},{"id":"1905.07790","title":"Correlation Coefficients and Semantic Textual Similarity","created":"2019-05-19","cited_by_count":20},{"id":"2011.12073","title":"Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis","created":"2020-11-24","cited_by_count":18},{"id":"2102.05975","title":"Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks","created":"2021-02-11","cited_by_count":17},{"id":"1707.01195","title":"The impossibility of \"fairness\": a generalized impossibility result for decisions","created":"2017-07-05","cited_by_count":12},{"id":"2005.02178","title":"IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization","created":"2020-05-02","cited_by_count":12},{"id":"2106.04753","title":"On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation","created":"2021-06-09","cited_by_count":12},{"id":"2203.02745","title":"The Impact of Differential Privacy on Group Disparity Mitigation","created":"2022-03-05","cited_by_count":11},{"id":"1812.09244","title":"Symbolic inductive bias for visually grounded learning of spoken language","created":"2018-12-21","cited_by_count":10},{"id":"2106.13203","title":"When Differential Privacy Meets Interpretability: A Case Study","created":"2021-06-24","cited_by_count":8},{"id":"2109.05772","title":"Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages","created":"2021-09-13","cited_by_count":8},{"id":"2101.04758","title":"Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling","created":"2021-01-12","cited_by_count":6},{"id":"2209.06529","title":"Data Privacy and Trustworthy Machine Learning","created":"2022-09-14","cited_by_count":6},{"id":"2109.05388","title":"The Impact of Positional Encodings on Multilingual Compression","created":"2021-09-11","cited_by_count":5}],"next_cursor":null}