{"total":108,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"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":"2406.10890","title":"RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models","created":"2024-06-16","cited_by_count":78,"area":"safety"},{"id":"2410.11143","title":"LLM Unlearning via Loss Adjustment with Only Forget Data","created":"2024-10-14","cited_by_count":75,"area":"safety"},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74,"area":null},{"id":"2406.17975","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","created":"2024-06-25","cited_by_count":59,"area":"safety"},{"id":"2406.18664","title":"Evaluating Copyright Takedown Methods for Language Models","created":"2024-06-26","cited_by_count":43,"area":null},{"id":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42,"area":"safety"},{"id":"2505.11953","title":"Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning","created":"2025-05-17","cited_by_count":39,"area":"safety"},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"area":"safety"},{"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":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18,"area":"safety"},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2403.15779","title":"The Frontier of Data Erasure: Machine Unlearning for Large Language Models","created":"2024-03-23","cited_by_count":17,"area":"safety"},{"id":"2505.13312","title":"GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection","created":"2025-05-19","cited_by_count":17,"area":"safety"},{"id":"2410.16618","title":"SoK: Dataset Copyright Auditing in Machine Learning Systems","created":"2024-10-22","cited_by_count":15,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2405.17423","title":"Privacy-Aware Visual Language Models","created":"2024-05-27","cited_by_count":12,"area":"mllm"},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2509.02820","title":"Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs","created":"2025-09-02","cited_by_count":11,"area":"safety"},{"id":"2510.19796","title":"Blackbox Model Provenance via Palimpsestic Membership Inference","created":"2025-10-22","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":"2406.13706","title":"Developing Story: Case Studies of Generative AI's Use in Journalism","created":"2024-06-19","cited_by_count":10,"area":null},{"id":"2502.00406","title":"Agents Are All You Need for LLM Unlearning","created":"2025-02-01","cited_by_count":10,"area":"agents"},{"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":"2409.19450","title":"Secret Use of Large Language Model (LLM)","created":"2024-09-28","cited_by_count":9,"area":null},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","cited_by_count":9,"area":"safety"},{"id":"2506.17863","title":"LLMs for Customized Marketing Content Generation and Evaluation at Scale","created":"2025-06-22","cited_by_count":9,"area":null},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","cited_by_count":9,"area":"lr"},{"id":"2511.04934","title":"Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding","created":"2025-11-07","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":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2604.00419","title":"G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs","created":"2026-04-01","cited_by_count":8,"area":"safety"},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2508.09603","title":"The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage","created":"2025-08-13","cited_by_count":7,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"area":"safety"},{"id":"2403.16139","title":"A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish","created":"2024-03-24","cited_by_count":6,"area":null},{"id":"2408.11546","title":"Memorization in In-Context Learning","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2408.16345","title":"The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization","created":"2024-08-29","cited_by_count":6,"area":"lr"},{"id":"2506.03142","title":"Not All Tokens Are Meant to Be Forgotten","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2506.19399","title":"Automated Detection of Pre-training Text in Black-box LLMs","created":"2025-06-24","cited_by_count":6,"area":null},{"id":"2602.06441","title":"Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning","created":"2026-02-06","cited_by_count":6,"area":"safety"},{"id":"2411.09224","title":"Programming with AI: Evaluating ChatGPT, Gemini, AlphaCode, and GitHub Copilot for Programmers","created":"2024-11-14","cited_by_count":5,"area":null},{"id":"2503.22948","title":"SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning","created":"2025-03-29","cited_by_count":5,"area":"alignment"},{"id":"2510.02962","title":"Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking","created":"2025-10-03","cited_by_count":5,"area":"safety"},{"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":"2406.14549","title":"Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2407.20105","title":"Strong Copyright Protection for Language Models via Adaptive Model Fusion","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2505.22945","title":"OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2403.15740","title":"Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training","created":"2024-03-23","cited_by_count":3,"area":"safety"},{"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":"2510.22376","title":"Label Smoothing Improves Gradient Ascent in LLM Unlearning","created":"2025-10-25","cited_by_count":3,"area":"safety"},{"id":"2512.08946","title":"Large Language Models as Search Engines: Societal Challenges","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2601.22020","title":"Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning","created":"2026-01-29","cited_by_count":3,"area":"mllm"},{"id":"2311.15716","title":"Justifiable Artificial Intelligence: Engineering Large Language Models for Legal Applications","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2404.19048","title":"A Framework for Real-time Safeguarding the Text Generation of Large Language Model","created":"2024-04-29","cited_by_count":2,"area":"safety"},{"id":"2407.08152","title":"Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)","created":"2024-07-11","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":"2504.04373","title":"StyleRec: A Benchmark Dataset for Prompt Recovery in Writing Style Transformation","created":"2025-04-06","cited_by_count":2,"area":null},{"id":"2505.13171","title":"Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2508.17681","title":"Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery","created":"2025-08-25","cited_by_count":2,"area":"safety"},{"id":"2509.20909","title":"LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2509.23362","title":"Dual-Space Smoothness for Robust and Balanced LLM Unlearning","created":"2025-09-27","cited_by_count":2,"area":"safety"},{"id":"2510.24256","title":"From Memorization to Reasoning in the Spectrum of Loss Curvature","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2601.09281","title":"STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2601.22030","title":"Per-parameter Task Arithmetic for Unlearning in Large Language Models","created":"2026-01-29","cited_by_count":2,"area":"safety"},{"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":"2605.16776","title":"Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning","created":"2026-05-16","cited_by_count":2,"area":"safety"},{"id":"2409.14050","title":"The use of GPT-4o and Other Large Language Models for the Improvement and Design of Self-Assessment Scales for Measurement of Interpersonal Communication Skills","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2502.17358","title":"DIS-CO: Discovering Copyrighted Content in VLMs Training Data","created":"2025-02-24","cited_by_count":1,"area":"mllm"},{"id":"2504.06658","title":"A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty","created":"2025-04-09","cited_by_count":1,"area":"safety"},{"id":"2508.20443","title":"Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2509.18836","title":"Bounded PCTL Model Checking of Large Language Model Outputs","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.15976","title":"Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization","created":"2025-10-13","cited_by_count":1,"area":"safety"},{"id":"2511.11914","title":"Forgetting-MarI: LLM Unlearning via Marginal Information Regularization","created":"2025-11-14","cited_by_count":1,"area":"safety"},{"id":"2606.06320","title":"Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance","created":"2026-06-04","cited_by_count":1,"area":"safety"},{"id":"2412.10257","title":"Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2506.12321","title":"Beyond Frequency: The Role of Redundancy in Large Language Model Memorization","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2506.20481","title":"Counterfactual Influence as a Distributional Quantity","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2510.25941","title":"RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline","created":"2025-10-29","cited_by_count":0,"area":"agents"},{"id":"2601.08840","title":"Consistency-Aware Editing for Entity-level Unlearning in Language Models","created":"2025-12-19","cited_by_count":0,"area":"safety"},{"id":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":"safety"},{"id":"2602.08632","title":"We Should Separate Memorization from Copyright","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.05871","title":"Retain-Neutral Surrogates for Min-Max Unlearning","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.24173","title":"Extracting Training Data from Diffusion Language Models via Infilling","created":"2026-05-22","cited_by_count":0,"area":"diffusion"},{"id":"2605.27020","title":"Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models","created":"2026-05-26","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}