{"total":118,"rows":[{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458,"area":null},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2212.03860","title":"Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models","created":"2022-12-07","cited_by_count":424,"area":"diffusion"},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312,"area":"safety"},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269,"area":null},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224,"area":"safety"},{"id":"2310.20150","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","created":"2023-10-31","cited_by_count":215,"area":"safety"},{"id":"2305.20086","title":"Understanding and Mitigating Copying in Diffusion Models","created":"2023-05-31","cited_by_count":209,"area":"diffusion"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148,"area":null},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2305.19256","title":"Ambient Diffusion: Learning Clean Distributions from Corrupted Data","created":"2023-05-30","cited_by_count":111,"area":null},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2406.01257","title":"What makes unlearning hard and what to do about it","created":"2024-06-03","cited_by_count":89,"area":"safety"},{"id":"2403.01218","title":"Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy","created":"2024-03-02","cited_by_count":82,"area":"safety"},{"id":"2302.04460","title":"Bag of Tricks for Training Data Extraction from Language Models","created":"2023-02-09","cited_by_count":70,"area":null},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69,"area":null},{"id":"2311.01797","title":"On the Generalization Properties of Diffusion Models","created":"2023-11-03","cited_by_count":68,"area":"diffusion"},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2303.11165","title":"Computationally Budgeted Continual Learning: What Does Matter?","created":"2023-03-20","cited_by_count":61,"area":null},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2405.03097","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","created":"2024-05-06","cited_by_count":43,"area":"safety"},{"id":"2210.10750","title":"Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries","created":"2022-10-19","cited_by_count":40,"area":"safety"},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2403.00871","title":"Teach LLMs to Phish: Stealing Private Information from Language Models","created":"2024-03-01","cited_by_count":32,"area":null},{"id":"2310.01424","title":"Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey","created":"2023-09-27","cited_by_count":30,"area":null},{"id":"2306.13384","title":"DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology","created":"2023-06-23","cited_by_count":29,"area":"diffusion"},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2307.04138","title":"On The Impact of Machine Learning Randomness on Group Fairness","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2401.12233","title":"Memorization in Self-Supervised Learning Improves Downstream Generalization","created":"2024-01-19","cited_by_count":18,"area":null},{"id":"2406.07687","title":"Adversarial Machine Unlearning","created":"2024-06-11","cited_by_count":16,"area":"safety"},{"id":"2305.12086","title":"Prefix Propagation: Parameter-Efficient Tuning for Long Sequences","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"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":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2501.05559","title":"Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2412.04648","title":"Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise","created":"2024-12-05","cited_by_count":13,"area":null},{"id":"2408.00001","title":"Replication in Visual Diffusion Models: A Survey and Outlook","created":"2024-07-07","cited_by_count":11,"area":"diffusion"},{"id":"2510.19796","title":"Blackbox Model Provenance via Palimpsestic Membership Inference","created":"2025-10-22","cited_by_count":11,"area":"safety"},{"id":"2305.05973","title":"Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2502.15680","title":"Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"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":"2310.16152","title":"Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering","created":"2023-10-24","cited_by_count":9,"area":null},{"id":"2402.01865","title":"What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2506.13009","title":"Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective","created":"2025-06-16","cited_by_count":9,"area":"safety"},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2411.07175","title":"Continual Memorization of Factoids in Language Models","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2503.06040","title":"Mitigating Memorization in LLMs using Activation Steering","created":"2025-03-08","cited_by_count":8,"area":"mechinterp"},{"id":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2406.15386","title":"U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI","created":"2024-04-22","cited_by_count":7,"area":null},{"id":"2407.19262","title":"Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications","created":"2024-07-27","cited_by_count":7,"area":null},{"id":"2410.02467","title":"SIDE: Surrogate Conditional Data Extraction from Diffusion Models","created":"2024-10-03","cited_by_count":7,"area":"diffusion"},{"id":"2502.05087","title":"Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2309.16082","title":"Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble","created":"2023-09-28","cited_by_count":6,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2409.14200","title":"Data-centric NLP Backdoor Defense from the Lens of Memorization","created":"2024-09-21","cited_by_count":6,"area":"safety"},{"id":"2412.02432","title":"Improved Localized Machine Unlearning Through the Lens of Memorization","created":"2024-12-03","cited_by_count":6,"area":"safety"},{"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":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2310.11739","title":"Unintended Memorization in Large ASR Models, and How to Mitigate It","created":"2023-10-18","cited_by_count":5,"area":null},{"id":"2502.10828","title":"The Vendiscope: An Algorithmic Microscope For Data Collections","created":"2025-02-15","cited_by_count":5,"area":null},{"id":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2305.19424","title":"Quantifying Overfitting: Evaluating Neural Network Performance through Analysis of Null Space","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2408.04983","title":"Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2502.07830","title":"Captured by Captions: On Memorization and its Mitigation in CLIP Models","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2505.23161","title":"Implicit Inversion turns CLIP into a Decoder","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2509.04304","title":"Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2307.16422","title":"Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution","created":"2023-07-31","cited_by_count":3,"area":null},{"id":"2404.02052","title":"Noise Masking Attacks and Defenses for Pretrained Speech Models","created":"2024-04-02","cited_by_count":3,"area":null},{"id":"2409.07025","title":"CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion","created":"2024-09-11","cited_by_count":3,"area":"diffusion"},{"id":"2510.02392","title":"KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning","created":"2025-10-01","cited_by_count":3,"area":"safety"},{"id":"2211.13416","title":"Data Origin Inference in Machine Learning","created":"2022-11-24","cited_by_count":2,"area":null},{"id":"2409.10482","title":"Schrodinger's Memory: Large Language Models","created":"2024-09-16","cited_by_count":2,"area":null},{"id":"2409.13953","title":"Training Large ASR Encoders with Differential Privacy","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2412.07261","title":"MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2512.08104","title":"AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2504.00170","title":"Backdoor Detection through Replicated Execution of Outsourced Training","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2507.14777","title":"Rethinking Memorization Measures and their Implications in Large Language Models","created":"2025-07-20","cited_by_count":1,"area":"lr"},{"id":"2512.07374","title":"Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning","created":"2025-12-08","cited_by_count":1,"area":"safety"},{"id":"2603.00140","title":"Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion","created":"2026-02-24","cited_by_count":1,"area":"diffusion"},{"id":"2606.26050","title":"Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2212.01907","title":"Understanding How Model Size Affects Few-shot Instruction Prompting","created":"2022-12-04","cited_by_count":0,"area":null},{"id":"2303.09067","title":"Secret-Keeping in Question Answering","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2311.09680","title":"Trustworthy Large Models in Vision: A Survey","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2402.12189","title":"Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships","created":"2024-02-19","cited_by_count":0,"area":"safety"},{"id":"2505.06284","title":"DMRL: Data- and Model-aware Reward Learning for Data Extraction","created":"2025-05-07","cited_by_count":0,"area":"alignment"},{"id":"2505.17664","title":"What is the role of memorization in Continual Learning?","created":"2025-05-23","cited_by_count":0,"area":null}],"next_cursor":"100"}