{"list":"other","total":52,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2306.05443","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","created":"2023-06-08","cited_by_count":222},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"1910.08902","title":"Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations","created":"2019-10-20","cited_by_count":119},{"id":"2210.14348","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","created":"2022-10-25","cited_by_count":108},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91},{"id":"2205.09148","title":"DDXPlus: A New Dataset For Automatic Medical Diagnosis","created":"2022-05-18","cited_by_count":88},{"id":"2305.03010","title":"Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence","created":"2023-05-04","cited_by_count":81},{"id":"2212.10025","title":"When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods","created":"2022-12-20","cited_by_count":75},{"id":"2211.01452","title":"MPCFormer: fast, performant and private Transformer inference with MPC","created":"2022-11-02","cited_by_count":69},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","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":"2205.02130","title":"The Limits of Word Level Differential Privacy","created":"2022-05-02","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":"2108.12944","title":"Selective Differential Privacy for Language Modeling","created":"2021-08-30","cited_by_count":62},{"id":"2104.07504","title":"Natural Language Understanding with Privacy-Preserving BERT","created":"2021-04-15","cited_by_count":55},{"id":"2401.07612","title":"Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications","created":"2024-01-15","cited_by_count":54},{"id":"2201.12675","title":"Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models","created":"2022-01-29","cited_by_count":53},{"id":"1910.08917","title":"Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text","created":"2019-10-20","cited_by_count":50},{"id":"2312.17484","title":"Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning","created":"2023-12-29","cited_by_count":45},{"id":"2305.06212","title":"Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services","created":"2023-05-10","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":"2309.03057","title":"Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection","created":"2023-09-06","cited_by_count":38},{"id":"1907.08736","title":"ER-AE: Differentially Private Text Generation for Authorship Anonymization","created":"2019-07-20","cited_by_count":35},{"id":"2106.11384","title":"Membership Inference on Word Embedding and Beyond","created":"2021-06-21","cited_by_count":35},{"id":"2305.13865","title":"Selective Pre-training for Private Fine-tuning","created":"2023-05-23","cited_by_count":23},{"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":"2305.18396","title":"LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers","created":"2023-05-28","cited_by_count":22},{"id":"2402.13846","title":"Large Language Models are Advanced Anonymizers","created":"2024-02-21","cited_by_count":22},{"id":"2303.13679","title":"Primer: Fast Private Transformer Inference on Encrypted Data","created":"2023-03-23","cited_by_count":20},{"id":"2205.10228","title":"You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas","created":"2022-04-26","cited_by_count":11},{"id":"2404.10464","title":"DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion","created":"2024-04-16","cited_by_count":9},{"id":"2401.13756","title":"NLICE: Synthetic Medical Record Generation for Effective Primary Healthcare Differential Diagnosis","created":"2024-01-24","cited_by_count":3}],"next_cursor":null}