{"list":"other","total":99,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"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":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2210.10341","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","created":"2022-10-19","cited_by_count":538},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1805.04049","title":"Exploiting Unintended Feature Leakage in Collaborative Learning","created":"2018-05-10","cited_by_count":520},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1907.05012","title":"Making AI Forget You: Data Deletion in Machine Learning","created":"2019-07-11","cited_by_count":465},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2003.10595","title":"Systematic Evaluation of Privacy Risks of Machine Learning Models","created":"2020-03-24","cited_by_count":292},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"1911.07135","title":"The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks","created":"2019-11-17","cited_by_count":246},{"id":"2203.03540","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","created":"2022-02-02","cited_by_count":238},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220},{"id":"2006.07709","title":"Auditing Differentially Private Machine Learning: How Private is Private SGD?","created":"2020-06-13","cited_by_count":218},{"id":"2004.00053","title":"Information Leakage in Embedding Models","created":"2020-03-31","cited_by_count":203},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201},{"id":"2205.12628","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","created":"2022-05-25","cited_by_count":200},{"id":"2101.04535","title":"Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning","created":"2021-01-11","cited_by_count":199},{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133},{"id":"1812.06469","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","created":"2018-12-16","cited_by_count":126},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113},{"id":"2104.07762","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","created":"2021-04-15","cited_by_count":93},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88},{"id":"1711.09050","title":"Ethical Challenges in Data-Driven Dialogue Systems","created":"2017-11-24","cited_by_count":86},{"id":"2101.01341","title":"Practical Blind Membership Inference Attack via Differential Comparisons","created":"2021-01-05","cited_by_count":78},{"id":"2010.06060","title":"BioMegatron: Larger Biomedical Domain Language Model","created":"2020-10-12","cited_by_count":76},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73},{"id":"2102.11845","title":"Learning with User-Level Privacy","created":"2021-02-23","cited_by_count":72},{"id":"1904.05506","title":"Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?","created":"2019-04-11","cited_by_count":71},{"id":"2009.10031","title":"Training Production Language Models without Memorizing User Data","created":"2020-09-21","cited_by_count":68},{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62},{"id":"2106.03216","title":"On Memorization in Probabilistic Deep Generative Models","created":"2021-06-06","cited_by_count":60},{"id":"2104.08305","title":"Membership Inference Attack Susceptibility of Clinical Language Models","created":"2021-04-16","cited_by_count":52},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52},{"id":"2002.10635","title":"Formalizing Data Deletion in the Context of the Right to be Forgotten","created":"2020-02-25","cited_by_count":50},{"id":"2210.10045","title":"SafeText: A Benchmark for Exploring Physical Safety in Language Models","created":"2022-10-18","cited_by_count":41},{"id":"2106.11384","title":"Membership Inference on Word Embedding and Beyond","created":"2021-06-21","cited_by_count":35},{"id":"2209.10505","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","created":"2022-09-21","cited_by_count":31},{"id":"2103.07567","title":"Privacy Regularization: Joint Privacy-Utility Optimization in Language Models","created":"2021-03-12","cited_by_count":30},{"id":"2203.13920","title":"Canary Extraction in Natural Language Understanding Models","created":"2022-03-25","cited_by_count":21},{"id":"2110.06452","title":"\"I need a better description'': An Investigation Into User Expectations For Differential Privacy","created":"2021-10-13","cited_by_count":17},{"id":"2205.04605","title":"Sentence-level Privacy for Document Embeddings","created":"2022-05-10","cited_by_count":16},{"id":"2009.05669","title":"Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics","created":"2020-09-11","cited_by_count":13},{"id":"2210.09306","title":"Mitigating Covertly Unsafe Text within Natural Language Systems","created":"2022-10-17","cited_by_count":13},{"id":"2206.04591","title":"Privacy Leakage in Text Classification: A Data Extraction Approach","created":"2022-06-09","cited_by_count":10},{"id":"2211.02956","title":"Privacy-Preserving Models for Legal Natural Language Processing","created":"2022-11-05","cited_by_count":10},{"id":"1507.00255","title":"ReCon: Revealing and Controlling PII Leaks in Mobile Network Traffic","created":"2015-07-01","cited_by_count":9},{"id":"2101.00036","title":"KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models","created":"2020-12-31","cited_by_count":7},{"id":"2210.11735","title":"Extracted BERT Model Leaks More Information than You Think!","created":"2022-10-21","cited_by_count":3},{"id":"2212.08619","title":"Planting and Mitigating Memorized Content in Predictive-Text Language Models","created":"2022-12-16","cited_by_count":1}],"next_cursor":null}