{"list":"other","total":80,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"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":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"1907.00503","title":"Modeling Tabular data using Conditional GAN","created":"2019-07-01","cited_by_count":699},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2209.15421","title":"TabDDPM: Modelling Tabular Data with Diffusion Models","created":"2022-09-30","cited_by_count":377},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"1605.02065","title":"Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds","created":"2016-05-06","cited_by_count":346},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"1311.0776","title":"The Composition Theorem for Differential Privacy","created":"2013-11-04","cited_by_count":297},{"id":"2210.06280","title":"Language Models are Realistic Tabular Data Generators","created":"2022-10-12","cited_by_count":294},{"id":"1802.08908","title":"Scalable Private Learning with PATE","created":"2018-02-24","cited_by_count":269},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"1802.06739","title":"Differentially Private Generative Adversarial Network","created":"2018-02-19","cited_by_count":235},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193},{"id":"2310.09656","title":"Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space","created":"2023-10-14","cited_by_count":186},{"id":"2303.10130","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","created":"2023-03-17","cited_by_count":176},{"id":"2102.08369","title":"CTAB-GAN: Effective Table Data Synthesizing","created":"2021-02-16","cited_by_count":156},{"id":"2001.09700","title":"DP-CGAN: Differentially Private Synthetic Data and Label Generation","created":"2020-01-27","cited_by_count":118},{"id":"2011.07018","title":"Synthetic Data -- Anonymisation Groundhog Day","created":"2020-11-13","cited_by_count":108},{"id":"2210.14348","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","created":"2022-10-25","cited_by_count":108},{"id":"2302.02041","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","created":"2023-02-04","cited_by_count":94},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88},{"id":"2302.13861","title":"Differentially Private Diffusion Models Generate Useful Synthetic Images","created":"2023-02-27","cited_by_count":86},{"id":"1502.02843","title":"Distributed Gaussian Processes","created":"2015-02-10","cited_by_count":84},{"id":"2002.11603","title":"DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation","created":"2020-02-26","cited_by_count":78},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76},{"id":"2204.00401","title":"CTAB-GAN+: Enhancing Tabular Data Synthesis","created":"2022-04-01","cited_by_count":70},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68},{"id":"2210.00038","title":"Differentially Private Optimization on Large Model at Small Cost","created":"2022-09-30","cited_by_count":65},{"id":"2305.15560","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","created":"2023-05-24","cited_by_count":65},{"id":"2307.03694","title":"Scalable Membership Inference Attacks via Quantile Regression","created":"2023-07-07","cited_by_count":65},{"id":"2211.06550","title":"TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data","created":"2022-11-12","cited_by_count":57},{"id":"2310.12746","title":"TabuLa: Harnessing Language Models for Tabular Data Synthesis","created":"2023-10-19","cited_by_count":42},{"id":"2312.17493","title":"Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning","created":"2023-12-29","cited_by_count":41},{"id":"2307.02106","title":"SoK: Privacy-Preserving Data Synthesis","created":"2023-07-05","cited_by_count":38},{"id":"2412.18626","title":"Why Do Large Language Models (LLMs) Struggle to Count Letters?","created":"2024-12-19","cited_by_count":38},{"id":"2206.15076","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","created":"2022-06-30","cited_by_count":36},{"id":"2102.01502","title":"ADePT: Auto-encoder based Differentially Private Text Transformation","created":"2021-01-29","cited_by_count":31},{"id":"2205.12900","title":"Pre-trained Perceptual Features Improve Differentially Private Image Generation","created":"2022-05-25","cited_by_count":28},{"id":"2306.10308","title":"Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing","created":"2023-06-17","cited_by_count":28},{"id":"2207.05295","title":"TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data","created":"2022-07-12","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":"2105.02866","title":"Membership Inference Attacks on Deep Regression Models for Neuroimaging","created":"2021-05-06","cited_by_count":22},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20},{"id":"2307.01701","title":"Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data","created":"2023-07-04","cited_by_count":18},{"id":"2403.00932","title":"Differentially Private Knowledge Distillation via Synthetic Text Generation","created":"2024-03-01","cited_by_count":18},{"id":"1704.05908","title":"An Interpretable Knowledge Transfer Model for Knowledge Base Completion","created":"2017-04-19","cited_by_count":17},{"id":"2103.05472","title":"Differentially Private Imaging via Latent Space Manipulation","created":"2021-03-08","cited_by_count":13},{"id":"2406.13985","title":"The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging","created":"2024-06-20","cited_by_count":13},{"id":"2409.07638","title":"Can We Count on LLMs? The Fixed-Effect Fallacy and Claims of GPT-4 Capabilities","created":"2024-09-11","cited_by_count":13},{"id":"2408.12249","title":"LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction","created":"2024-08-22","cited_by_count":9},{"id":"1902.01499","title":"Differentially Private Release of High-Dimensional Datasets using the Gaussian Copula","created":"2019-02-04","cited_by_count":8},{"id":"1301.3226","title":"The Expressive Power of Word Embeddings","created":"2013-01-15","cited_by_count":7},{"id":"2412.02467","title":"DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators","created":"2024-12-03","cited_by_count":5}],"next_cursor":null}