{"total":94,"rows":[{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2410.07163","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","created":"2024-10-09","cited_by_count":172,"area":"lr"},{"id":"2506.12618","title":"OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics","created":"2025-06-14","cited_by_count":83,"area":"safety"},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2406.10209","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","created":"2024-06-14","cited_by_count":50,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"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":"2407.07087","title":"CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation","created":"2024-07-09","cited_by_count":35,"area":null},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35,"area":null},{"id":"2406.12975","title":"SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation","created":"2024-06-18","cited_by_count":34,"area":null},{"id":"2406.17746","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon","created":"2024-06-25","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":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"id":"2410.03523","title":"A Probabilistic Perspective on Unlearning and Alignment for Large Language Models","created":"2024-10-04","cited_by_count":21,"area":"alignment"},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2405.05990","title":"Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models","created":"2024-05-09","cited_by_count":17,"area":null},{"id":"2601.02671","title":"Extracting books from production language models","created":"2026-01-06","cited_by_count":17,"area":"safety"},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2506.09227","title":"SoK: Machine Unlearning for Large Language Models","created":"2025-06-10","cited_by_count":11,"area":"safety"},{"id":"2405.15523","title":"The Mosaic Memory of Large Language Models","created":"2024-05-24","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":"2502.11169","title":"CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Model","created":"2025-02-16","cited_by_count":9,"area":"lr"},{"id":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","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":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2412.20760","title":"Attributing Culture-Conditioned Generations to Pretraining Corpora","created":"2024-12-30","cited_by_count":8,"area":null},{"id":"2506.00688","title":"Existing Large Language Model Unlearning Evaluations Are Inconclusive","created":"2025-05-31","cited_by_count":8,"area":"safety"},{"id":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"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":"2505.17160","title":"Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting","created":"2025-05-22","cited_by_count":7,"area":"safety"},{"id":"2507.07229","title":"SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2411.01789","title":"Generating executable oracles to check conformance of client code to requirements of JDK Javadocs using LLMs","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2509.14278","title":"Beyond Data Privacy: New Privacy Risks for Large Language Models","created":"2025-09-16","cited_by_count":6,"area":null},{"id":"2510.16629","title":"On the Impossibility of Retrain Equivalence in Machine Unlearning","created":"2025-10-18","cited_by_count":6,"area":"safety"},{"id":"2408.06502","title":"Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers","created":"2024-08-12","cited_by_count":5,"area":null},{"id":"2409.14513","title":"Order of Magnitude Speedups for LLM Membership Inference","created":"2024-09-22","cited_by_count":5,"area":"safety"},{"id":"2412.08127","title":"Evil twins are not that evil: Qualitative insights into machine-generated prompts","created":"2024-12-11","cited_by_count":5,"area":null},{"id":"2502.15010","title":"Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models","created":"2025-02-20","cited_by_count":5,"area":"safety"},{"id":"2504.01738","title":"Style over Substance: Distilled Language Models Reason Via Stylistic Replication","created":"2025-04-02","cited_by_count":5,"area":"lr"},{"id":"2505.03019","title":"Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2505.05225","title":"QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation","created":"2025-05-08","cited_by_count":5,"area":null},{"id":"2510.14205","title":"DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans","created":"2025-10-16","cited_by_count":5,"area":"agents"},{"id":"2512.19025","title":"The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation","created":"2025-12-22","cited_by_count":5,"area":"safety"},{"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":"2407.13493","title":"Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2503.07697","title":"PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"safety"},{"id":"2503.12314","title":"Empirical Privacy Variance","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2504.04877","title":"System Log Parsing with Large Language Models: A Review","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2506.07458","title":"KScope: A Framework for Characterizing the Knowledge Status of Language Models","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2506.13181","title":"Align-then-Unlearn: Embedding Alignment for LLM Unlearning","created":"2025-06-16","cited_by_count":3,"area":"safety"},{"id":"2506.20856","title":"Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA","created":"2025-06-25","cited_by_count":3,"area":"safety"},{"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":"2510.00496","title":"Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2511.05518","title":"Retracing the Past: LLMs Emit Training Data When They Get Lost","created":"2025-10-27","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":"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":"2412.18497","title":"Neuron-Level Differentiation of Memorization and Generalization in Large Language Models","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2502.05159","title":"A Lightweight Method to Disrupt Memorized Sequences in LLM","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2509.20909","title":"LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.20799","title":"Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2602.18733","title":"A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2606.13873","title":"Natively Unlearnable Large Language Models","created":"2026-06-11","cited_by_count":2,"area":"safety"},{"id":"2502.16290","title":"Interrogating LLM design under a fair learning doctrine","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2505.09500","title":"Layered Unlearning for Adversarial Relearning","created":"2025-05-14","cited_by_count":1,"area":"safety"},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2505.13362","title":"Dynamic Probabilistic Noise Injection for Membership Inference Defense","created":"2025-05-19","cited_by_count":1,"area":"safety"},{"id":"2506.06060","title":"Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2507.06056","title":"Data Compressibility Quantifies LLM Memorization","created":"2025-07-08","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":"2510.08813","title":"The Model's Language Matters: A Comparative Privacy Analysis of LLMs","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2510.21322","title":"Leverage Unlearning to Sanitize LLMs","created":"2025-10-24","cited_by_count":1,"area":"safety"},{"id":"2601.10496","title":"Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.15377","title":"Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2604.18697","title":"Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs","created":"2026-04-20","cited_by_count":1,"area":"safety"},{"id":"2605.30642","title":"Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?","created":"2026-05-28","cited_by_count":1,"area":"diffusion"},{"id":"2501.02407","title":"Towards the Anonymization of the Language Modeling","created":"2025-01-05","cited_by_count":0,"area":null},{"id":"2510.20428","title":"An Empirical Study of Sample Selection Strategies for Large Language Model Repair","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2510.22052","title":"A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents","created":"2025-10-24","cited_by_count":0,"area":"agents"},{"id":"2512.03310","title":"Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.11194","title":"Beyond Memorization: Selective Learning for Copyright-Safe Diffusion Model Training","created":"2025-12-12","cited_by_count":0,"area":"diffusion"},{"id":"2603.21658","title":"A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.12574","title":"DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction","created":"2026-05-12","cited_by_count":0,"area":"mllm"},{"id":"2607.12649","title":"Extractable Memorization From First Principles","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.24688","title":"Beyond Scale and Generation: Understanding Language Model-based Entity Matching","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.00700","title":"Value Over Language Model: Detecting Original Contribution in Writing","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.02418","title":"Mitigating Private Data Leakage in LLMs with Whiteout","created":"2026-10-01","cited_by_count":0,"area":"safety"}],"next_cursor":null}