{"list":"other","total":100,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2110.14795","title":"MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification","created":"2021-10-27","cited_by_count":690},{"id":"1710.05006","title":"Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2017-10-13","cited_by_count":549},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277},{"id":"1802.08908","title":"Scalable Private Learning with PATE","created":"2018-02-24","cited_by_count":269},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175},{"id":"2009.12756","title":"Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval","created":"2020-09-27","cited_by_count":162},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136},{"id":"2208.11625","title":"PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model","created":"2022-08-24","cited_by_count":134},{"id":"1910.08902","title":"Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations","created":"2019-10-20","cited_by_count":119},{"id":"1711.05217","title":"Controllable Abstractive Summarization","created":"2017-11-14","cited_by_count":110},{"id":"2210.14348","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","created":"2022-10-25","cited_by_count":108},{"id":"2309.11765","title":"Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation","created":"2023-09-21","cited_by_count":96},{"id":"2305.15594","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","created":"2023-05-24","cited_by_count":83},{"id":"2106.01221","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","created":"2021-06-02","cited_by_count":77},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76},{"id":"2311.13647","title":"Language Model Inversion","created":"2023-11-22","cited_by_count":68},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67},{"id":"2306.01684","title":"Harnessing large-language models to generate private synthetic text","created":"2023-06-02","cited_by_count":65},{"id":"2304.06762","title":"Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study","created":"2023-04-13","cited_by_count":63},{"id":"2310.16111","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","created":"2023-10-24","cited_by_count":63},{"id":"2312.06717","title":"Privacy Issues in Large Language Models: A Survey","created":"2023-12-11","cited_by_count":60},{"id":"2206.00216","title":"THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption","created":"2022-06-01","cited_by_count":57},{"id":"2312.03724","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","created":"2023-11-27","cited_by_count":57},{"id":"2308.15367","title":"Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation","created":"2023-08-29","cited_by_count":54},{"id":"2207.01193","title":"A Customized Text Sanitization Mechanism with Differential Privacy","created":"2022-07-04","cited_by_count":52},{"id":"2305.01639","title":"Privacy-Preserving In-Context Learning for Large Language Models","created":"2023-05-02","cited_by_count":50},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49},{"id":"1705.08963","title":"DeepSecure: Scalable Provably-Secure Deep Learning","created":"2017-05-24","cited_by_count":48},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45},{"id":"2107.07928","title":"TEM: High Utility Metric Differential Privacy on Text","created":"2021-07-16","cited_by_count":43},{"id":"2010.11947","title":"A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric","created":"2020-10-22","cited_by_count":42},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40},{"id":"2309.03057","title":"Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection","created":"2023-09-06","cited_by_count":38},{"id":"2403.03129","title":"CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following","created":"2024-03-05","cited_by_count":33},{"id":"2305.14888","title":"Privacy Implications of Retrieval-Based Language Models","created":"2023-05-24","cited_by_count":32},{"id":"2209.10505","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","created":"2022-09-21","cited_by_count":31},{"id":"2006.14170","title":"Towards Differentially Private Text Representations","created":"2020-06-25","cited_by_count":29},{"id":"2211.07864","title":"Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning","created":"2022-11-15","cited_by_count":29},{"id":"2010.05253","title":"A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysis","created":"2020-10-11","cited_by_count":26},{"id":"2110.00394","title":"Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning","created":"2021-10-01","cited_by_count":25},{"id":"2306.08223","title":"Protecting User Privacy in Remote Conversational Systems: A Privacy-Preserving framework based on text sanitization","created":"2023-06-14","cited_by_count":23},{"id":"2108.12318","title":"CAPE: Context-Aware Private Embeddings for Private Language Learning","created":"2021-08-27","cited_by_count":22},{"id":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20},{"id":"2403.00932","title":"Differentially Private Knowledge Distillation via Synthetic Text Generation","created":"2024-03-01","cited_by_count":18},{"id":"2303.12247","title":"Exploring the Benefits of Visual Prompting in Differential Privacy","created":"2023-03-22","cited_by_count":17},{"id":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17},{"id":"2205.04605","title":"Sentence-level Privacy for Document Embeddings","created":"2022-05-10","cited_by_count":16},{"id":"2311.15792","title":"Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective","created":"2023-11-27","cited_by_count":16},{"id":"1604.07312","title":"Endgame Analysis of Dou Shou Qi","created":"2016-04-25","cited_by_count":11},{"id":"2403.05681","title":"DP-TabICL: In-Context Learning with Differentially Private Tabular Data","created":"2024-03-08","cited_by_count":11},{"id":"2201.12333","title":"A Joint Exponential Mechanism For Differentially Private Top-$k$","created":"2022-01-28","cited_by_count":10},{"id":"2402.08227","title":"Privacy-Preserving Language Model Inference with Instance Obfuscation","created":"2024-02-13","cited_by_count":7},{"id":"2403.09720","title":"Fine-tuning vs Prompting, Can Language Models Understand Human Values?","created":"2024-03-12","cited_by_count":4},{"id":"2008.00774","title":"Elsevier OA CC-By Corpus","created":"2020-08-03","cited_by_count":3}],"next_cursor":null}