{"list":"other","total":68,"rows":[{"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"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":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"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":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1806.01246","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","created":"2018-06-04","cited_by_count":498},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"id":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301},{"id":"1908.11229","title":"White-box vs Black-box: Bayes Optimal Strategies for Membership Inference","created":"2019-08-29","cited_by_count":271},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230},{"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":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195},{"id":"1807.05852","title":"Machine Learning with Membership Privacy using Adversarial Regularization","created":"2018-07-16","cited_by_count":186},{"id":"1906.11798","title":"Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference","created":"2019-06-27","cited_by_count":175},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136},{"id":"2402.15938","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","created":"2024-02-24","cited_by_count":122},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119},{"id":"2005.10881","title":"Revisiting Membership Inference Under Realistic Assumptions","created":"2020-05-21","cited_by_count":112},{"id":"2011.07018","title":"Synthetic Data -- Anonymisation Groundhog Day","created":"2020-11-13","cited_by_count":108},{"id":"2310.13771","title":"Copyright Violations and Large Language Models","created":"2023-10-20","cited_by_count":108},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103},{"id":"2312.16337","title":"Task Contamination: Language Models May Not Be Few-Shot Anymore","created":"2023-12-26","cited_by_count":99},{"id":"1802.04889","title":"Understanding Membership Inferences on Well-Generalized Learning Models","created":"2018-02-13","cited_by_count":90},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88},{"id":"1711.09050","title":"Ethical Challenges in Data-Driven Dialogue Systems","created":"2017-11-24","cited_by_count":86},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73},{"id":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53},{"id":"2309.10677","title":"Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation","created":"2023-09-19","cited_by_count":48},{"id":"2311.06233","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","created":"2023-11-10","cited_by_count":47},{"id":"2310.06714","title":"Exploring Memorization in Fine-tuned Language Models","created":"2023-10-10","cited_by_count":45},{"id":"2402.07148","title":"X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design","created":"2024-02-11","cited_by_count":42},{"id":"2402.10892","title":"Proving membership in LLM pretraining data via data watermarks","created":"2024-02-16","cited_by_count":40},{"id":"2402.09363","title":"Copyright Traps for Large Language Models","created":"2024-02-14","cited_by_count":37},{"id":"2006.07490","title":"Understanding Unintended Memorization in Federated Learning","created":"2020-06-12","cited_by_count":36},{"id":"2405.13769","title":"Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation","created":"2024-05-22","cited_by_count":32},{"id":"2306.10308","title":"Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing","created":"2023-06-17","cited_by_count":28},{"id":"2208.11180","title":"Auditing Membership Leakages of Multi-Exit Networks","created":"2022-08-23","cited_by_count":27},{"id":"2312.04782","title":"Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs","created":"2023-12-08","cited_by_count":27},{"id":"2406.13236","title":"Data Contamination Can Cross Language Barriers","created":"2024-06-19","cited_by_count":26},{"id":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25},{"id":"2406.01333","title":"Probing Language Models for Pre-training Data Detection","created":"2024-06-03","cited_by_count":25},{"id":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","cited_by_count":24}],"next_cursor":null}