{"list":"other","total":70,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"1802.08908","title":"Scalable Private Learning with PATE","created":"2018-02-24","cited_by_count":269},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"id":"1908.10530","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","created":"2019-08-28","cited_by_count":204},{"id":"2106.02848","title":"Numerical Composition of Differential Privacy","created":"2021-06-05","cited_by_count":180},{"id":"1902.00098","title":"The Second Conversational Intelligence Challenge (ConvAI2)","created":"2019-01-31","cited_by_count":179},{"id":"1809.08267","title":"Neural Approaches to Conversational AI","created":"2018-09-21","cited_by_count":165},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"2001.09700","title":"DP-CGAN: Differentially Private Synthetic Data and Label Generation","created":"2020-01-27","cited_by_count":118},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2006.08265","title":"GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators","created":"2020-06-15","cited_by_count":117},{"id":"1911.11607","title":"Deep Learning with Gaussian Differential Privacy","created":"2019-11-26","cited_by_count":114},{"id":"1405.7085","title":"Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds","created":"2014-05-27","cited_by_count":107},{"id":"2110.03620","title":"Hyperparameter Tuning with Renyi Differential Privacy","created":"2021-10-07","cited_by_count":104},{"id":"2007.03813","title":"Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification","created":"2020-07-07","cited_by_count":90},{"id":"2010.02772","title":"InstaHide: Instance-hiding Schemes for Private Distributed Learning","created":"2020-10-06","cited_by_count":90},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86},{"id":"1908.07643","title":"AdaCliP: Adaptive Clipping for Private SGD","created":"2019-08-20","cited_by_count":77},{"id":"1811.07971","title":"Private Selection from Private Candidates","created":"2018-11-19","cited_by_count":75},{"id":"2009.10031","title":"Training Production Language Models without Memorizing User Data","created":"2020-09-21","cited_by_count":68},{"id":"1808.10122","title":"Learning Neural Templates for Text Generation","created":"2018-08-30","cited_by_count":61},{"id":"2010.09063","title":"Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization","created":"2020-10-18","cited_by_count":58},{"id":"1808.09408","title":"Privacy-preserving Neural Representations of Text","created":"2018-08-28","cited_by_count":54},{"id":"2012.11774","title":"Differentially Private Synthetic Medical Data Generation using Convolutional GANs","created":"2020-12-22","cited_by_count":52},{"id":"2009.03106","title":"Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping","created":"2020-09-07","cited_by_count":47},{"id":"2009.05886","title":"Differentially Private Language Models Benefit from Public Pre-training","created":"2020-09-13","cited_by_count":47},{"id":"2106.13756","title":"Private Adaptive Gradient Methods for Convex Optimization","created":"2021-06-25","cited_by_count":46},{"id":"1510.01799","title":"Efficient Per-Example Gradient Computations","created":"2015-10-07","cited_by_count":42},{"id":"2010.06053","title":"TextHide: Tackling Data Privacy in Language Understanding Tasks","created":"2020-10-12","cited_by_count":33},{"id":"2103.07567","title":"Privacy Regularization: Joint Privacy-Utility Optimization in Language Models","created":"2021-03-12","cited_by_count":30},{"id":"2102.03013","title":"Fast and Memory Efficient Differentially Private-SGD via JL Projections","created":"2021-02-05","cited_by_count":29},{"id":"2107.14586","title":"An Efficient DP-SGD Mechanism for Large Scale NLP Models","created":"2021-07-14","cited_by_count":27},{"id":"1905.07002","title":"Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models","created":"2019-05-16","cited_by_count":20},{"id":"2007.11934","title":"Private Post-GAN Boosting","created":"2020-07-23","cited_by_count":20},{"id":"2103.01294","title":"Wide Network Learning with Differential Privacy","created":"2021-03-01","cited_by_count":17},{"id":"2104.11838","title":"On a Utilitarian Approach to Privacy Preserving Text Generation","created":"2021-04-23","cited_by_count":17}],"next_cursor":null}