{"total":85,"rows":[{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400,"area":null},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"area":null},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148,"area":null},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136,"area":null},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62,"area":null},{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62,"area":null},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61,"area":null},{"id":"2107.08444","title":"A Theory of PAC Learnability of Partial Concept Classes","created":"2021-07-18","cited_by_count":60,"area":null},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2201.12675","title":"Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models","created":"2022-01-29","cited_by_count":53,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2106.13329","title":"Covariance-Aware Private Mean Estimation Without Private Covariance Estimation","created":"2021-06-24","cited_by_count":46,"area":null},{"id":"2410.19482","title":"Measuring memorization in language models via probabilistic extraction","created":"2024-10-25","cited_by_count":41,"area":null},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2205.13621","title":"Differentially Private Decoding in Large Language Models","created":"2022-05-26","cited_by_count":34,"area":null},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31,"area":null},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28,"area":null},{"id":"2209.10015","title":"Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics","created":"2022-09-20","cited_by_count":26,"area":null},{"id":"2307.01827","title":"Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses","created":"2023-07-04","cited_by_count":26,"area":null},{"id":"2204.10830","title":"Memory Bounds for Continual Learning","created":"2022-04-22","cited_by_count":19,"area":null},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2401.12233","title":"Memorization in Self-Supervised Learning Improves Downstream Generalization","created":"2024-01-19","cited_by_count":18,"area":null},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16,"area":null},{"id":"2303.01673","title":"Near Optimal Memory-Regret Tradeoff for Online Learning","created":"2023-03-03","cited_by_count":15,"area":null},{"id":"2202.09889","title":"Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression","created":"2022-02-20","cited_by_count":14,"area":null},{"id":"2302.01428","title":"Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation","created":"2023-02-02","cited_by_count":14,"area":null},{"id":"2306.01181","title":"TMI! Finetuned Models Leak Private Information from their Pretraining Data","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2402.09327","title":"Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization","created":"2024-02-14","cited_by_count":14,"area":null},{"id":"2110.04328","title":"Distinguishing rule- and exemplar-based generalization in learning systems","created":"2021-10-08","cited_by_count":12,"area":null},{"id":"2206.04743","title":"Strong Memory Lower Bounds for Learning Natural Models","created":"2022-06-09","cited_by_count":11,"area":null},{"id":"2204.09606","title":"Detecting Unintended Memorization in Language-Model-Fused ASR","created":"2022-04-20","cited_by_count":10,"area":null},{"id":"2206.04591","title":"Privacy Leakage in Text Classification: A Data Extraction Approach","created":"2022-06-09","cited_by_count":10,"area":null},{"id":"2402.18726","title":"Unveiling Privacy, Memorization, and Input Curvature Links","created":"2024-02-28","cited_by_count":10,"area":null},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2302.05707","title":"On Differential Privacy and Adaptive Data Analysis with Bounded Space","created":"2023-02-11","cited_by_count":9,"area":null},{"id":"2302.13181","title":"Data-Copying in Generative Models: A Formal Framework","created":"2023-02-25","cited_by_count":9,"area":null},{"id":"2304.03545","title":"AI Model Disgorgement: Methods and Choices","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2510.12066","title":"AI Agents as Universal Task Solvers","created":"2025-10-14","cited_by_count":9,"area":null},{"id":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2101.05405","title":"Training Data Leakage Analysis in Language Models","created":"2021-01-14","cited_by_count":7,"area":null},{"id":"2112.08798","title":"Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2207.11621","title":"A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2306.13789","title":"Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models","created":"2023-06-23","cited_by_count":6,"area":null},{"id":"2310.05337","title":"What do larger image classifiers memorise?","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2502.16570","title":"Entropy-Lens: Uncovering Decision Strategies in LLMs","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2503.07501","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2506.01855","title":"Trade-offs in Data Memorization via Strong Data Processing Inequalities","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2302.04963","title":"Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal","created":"2023-02-09","cited_by_count":5,"area":null},{"id":"2305.09579","title":"Private Everlasting Prediction","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2503.01630","title":"Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2305.05208","title":"Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2306.12534","title":"Memory-Query Tradeoffs for Randomized Convex Optimization","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2311.13447","title":"Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates","created":"2023-11-22","cited_by_count":4,"area":null},{"id":"2509.18014","title":"Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2401.14931","title":"Do LLMs Dream of Ontologies?","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2506.09591","title":"Memorization in Language Models through the Lens of Intrinsic Dimension","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2509.22214","title":"A Law of Data Reconstruction for Random Features (and Beyond)","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2604.08519","title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2212.04461","title":"Leveraging Unlabeled Data to Track Memorization","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2310.04015","title":"Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2311.09615","title":"On Retrieval Augmentation and the Limitations of Language Model Training","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2502.11893","title":"Rethinking Benign Overfitting in Two-Layer Neural Networks","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2602.00906","title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2205.14553","title":"Long-Tailed Learning Requires Feature Learning","created":"2022-05-29","cited_by_count":1,"area":null},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2404.06720","title":"Gradient Descent is Pareto-Optimal in the Oracle Complexity and Memory Tradeoff for Feasibility Problems","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2509.00303","title":"Access Paths for Efficient Ordering with Large Language Models","created":"2025-08-30","cited_by_count":1,"area":null},{"id":"2405.03004","title":"Exploring prompts to elicit memorization in masked language model-based named entity recognition","created":"2024-05-05","cited_by_count":0,"area":null},{"id":"2411.06916","title":"Slowing Down Forgetting in Continual Learning","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2505.19019","title":"Querying Kernel Methods Suffices for Reconstructing their Training Data","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2506.16460","title":"Black-Box Privacy Attacks on Shared Representations in Multitask Learning","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2509.20463","title":"Efficiently Attacking Memorization Scores","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2602.07999","title":"Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2602.08632","title":"We Should Separate Memorization from Copyright","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2607.12354","title":"Reducing information dependency does not cause training data privacy. Adversarially non-robust features do","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.24827","title":"Stronger Memory-Query Tradeoffs for Convex Optimization: The Limitations of Subquadratic Memory","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.27782","title":"Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.09206","title":"An Accuracy-Information Tradeoff for Loss-Difference Conditional Mutual Information","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}