{"total":122,"rows":[{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"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":"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":"2403.01267","title":"Dissecting Language Models: Machine Unlearning via Selective Pruning","created":"2024-03-02","cited_by_count":42,"area":"safety"},{"id":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"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":"2311.15766","title":"Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges","created":"2023-11-27","cited_by_count":38,"area":"safety"},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38,"area":"safety"},{"id":"2503.01854","title":"A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models","created":"2025-02-22","cited_by_count":34,"area":"safety"},{"id":"2406.09179","title":"Towards Effective Evaluations and Comparisons for LLM Unlearning Methods","created":"2024-06-13","cited_by_count":27,"area":"safety"},{"id":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2404.05188","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","created":"2024-04-08","cited_by_count":19,"area":"safety"},{"id":"2406.11780","title":"Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs","created":"2024-06-17","cited_by_count":18,"area":"safety"},{"id":"2407.11867","title":"Targeted Unlearning with Single Layer Unlearning Gradient","created":"2024-07-16","cited_by_count":18,"area":"safety"},{"id":"2406.14796","title":"MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning","created":"2024-06-21","cited_by_count":17,"area":"safety"},{"id":"2410.09591","title":"Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy","created":"2024-10-12","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":"2410.02684","title":"HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2410.15153","title":"Evaluating Deep Unlearning in Large Language Models","created":"2024-10-19","cited_by_count":14,"area":"safety"},{"id":"2504.04626","title":"Exact Unlearning of Finetuning Data via Model Merging at Scale","created":"2025-04-06","cited_by_count":14,"area":"safety"},{"id":"2506.05735","title":"Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness","created":"2025-06-06","cited_by_count":14,"area":"safety"},{"id":"2406.13348","title":"Textual Unlearning Gives a False Sense of Unlearning","created":"2024-06-19","cited_by_count":13,"area":"safety"},{"id":"2502.10525","title":"Towards Watermarking of Open-Source LLMs","created":"2025-02-14","cited_by_count":13,"area":"safety"},{"id":"2408.00376","title":"On the Limitations and Prospects of Machine Unlearning for Generative AI","created":"2024-08-01","cited_by_count":12,"area":"safety"},{"id":"2410.06467","title":"WAPITI: A Watermark for Finetuned Open-Source LLMs","created":"2024-10-09","cited_by_count":12,"area":"safety"},{"id":"2503.09117","title":"GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs","created":"2025-03-12","cited_by_count":12,"area":"safety"},{"id":"2504.10185","title":"LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks","created":"2025-04-14","cited_by_count":12,"area":"safety"},{"id":"2506.09227","title":"SoK: Machine Unlearning for Large Language Models","created":"2025-06-10","cited_by_count":11,"area":"safety"},{"id":"2506.14003","title":"Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs","created":"2025-06-16","cited_by_count":11,"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":"2410.05583","title":"NegMerge: Sign-Consensual Weight Merging for Machine Unlearning","created":"2024-10-08","cited_by_count":9,"area":"safety"},{"id":"2412.08559","title":"Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning","created":"2024-12-11","cited_by_count":9,"area":"safety"},{"id":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","cited_by_count":9,"area":"safety"},{"id":"2512.07375","title":"LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples","created":"2025-12-08","cited_by_count":8,"area":"safety"},{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2603.01285","title":"Attention Smoothing Is All You Need For Unlearning","created":"2026-03-01","cited_by_count":7,"area":"safety"},{"id":"2412.16780","title":"Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification","created":"2024-12-21","cited_by_count":6,"area":"safety"},{"id":"2506.03142","title":"Not All Tokens Are Meant to Be Forgotten","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2508.21300","title":"Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning","created":"2025-08-29","cited_by_count":6,"area":"safety"},{"id":"2510.17021","title":"Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning","created":"2025-10-19","cited_by_count":6,"area":"safety"},{"id":"2601.00590","title":"SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation","created":"2026-01-02","cited_by_count":6,"area":"safety"},{"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":"2411.18280","title":"Neutralizing Backdoors through Information Conflicts for Large Language Models","created":"2024-11-27","cited_by_count":5,"area":"safety"},{"id":"2502.19982","title":"Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models","created":"2025-02-27","cited_by_count":5,"area":"safety"},{"id":"2505.24379","title":"Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM","created":"2025-05-30","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":"2505.10859","title":"Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning","created":"2025-05-16","cited_by_count":4,"area":"safety"},{"id":"2505.15209","title":"DUSK: Do Not Unlearn Shared Knowledge","created":"2025-05-21","cited_by_count":4,"area":"safety"},{"id":"2507.11128","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2509.24675","title":"Understanding the Dilemma of Unlearning for Large Language Models","created":"2025-09-29","cited_by_count":4,"area":"safety"},{"id":"2602.06248","title":"REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop","created":"2026-02-05","cited_by_count":4,"area":"safety"},{"id":"2602.10568","title":"Gauss-Newton Unlearning for the LLM Era","created":"2026-02-11","cited_by_count":4,"area":"safety"},{"id":"2406.09391","title":"A More Practical Approach to Machine Unlearning","created":"2024-06-13","cited_by_count":3,"area":"safety"},{"id":"2501.02373","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","created":"2025-01-04","cited_by_count":3,"area":"safety"},{"id":"2504.19333","title":"Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing","created":"2025-04-27","cited_by_count":3,"area":"safety"},{"id":"2601.21283","title":"DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher","created":"2026-01-29","cited_by_count":3,"area":"safety"},{"id":"2604.09544","title":"Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types","created":"2026-04-10","cited_by_count":3,"area":"safety"},{"id":"2411.00204","title":"RESTOR: Knowledge Recovery in Machine Unlearning","created":"2024-10-31","cited_by_count":2,"area":"safety"},{"id":"2506.20941","title":"Revisiting the Past: Data Unlearning with Model State History","created":"2025-06-26","cited_by_count":2,"area":"safety"},{"id":"2509.23362","title":"Dual-Space Smoothness for Robust and Balanced LLM Unlearning","created":"2025-09-27","cited_by_count":2,"area":"safety"},{"id":"2512.16297","title":"Feature-Selective Representation Misdirection for Machine Unlearning","created":"2025-12-18","cited_by_count":2,"area":"safety"},{"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":"2601.22589","title":"FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery","created":"2026-01-30","cited_by_count":2,"area":"safety"},{"id":"2603.02436","title":"TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models","created":"2026-03-02","cited_by_count":2,"area":"safety"},{"id":"2604.10636","title":"Mitigating Privacy Risk via Forget Set-Free Unlearning","created":"2026-04-12","cited_by_count":2,"area":"safety"},{"id":"2605.01129","title":"Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set","created":"2026-05-01","cited_by_count":2,"area":"safety"},{"id":"2605.31293","title":"Divergence Decoding: Inference-Time Unlearning via Auxiliary Models","created":"2026-05-29","cited_by_count":2,"area":"safety"},{"id":"2412.06846","title":"Classifier-free guidance in LLMs Safety","created":"2024-12-08","cited_by_count":1,"area":"safety"},{"id":"2505.09500","title":"Layered Unlearning for Adversarial Relearning","created":"2025-05-14","cited_by_count":1,"area":"safety"},{"id":"2506.15076","title":"Learning-Time Encoding Shapes Unlearning in LLMs","created":"2025-06-18","cited_by_count":1,"area":"safety"},{"id":"2508.21004","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","created":"2025-08-28","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":"2511.19009","title":"Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2602.06623","title":"Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2602.12138","title":"BlackCATT: Black-box Collusion Aware Traitor Tracing in Federated Learning","created":"2026-02-12","cited_by_count":1,"area":"safety"},{"id":"2604.04231","title":"Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization","created":"2026-04-05","cited_by_count":1,"area":"safety"},{"id":"2604.23141","title":"UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks","created":"2026-04-25","cited_by_count":1,"area":"safety"},{"id":"2605.02196","title":"DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning","created":"2026-05-04","cited_by_count":1,"area":"safety"},{"id":"2605.18993","title":"Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task Arithmetic","created":"2026-05-18","cited_by_count":1,"area":"safety"},{"id":"2607.01686","title":"WARP: Weight-Space Analysis for Recovering Training Data Portfolios","created":"2026-07-02","cited_by_count":1,"area":"safety"},{"id":"2607.19442","title":"Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification","created":"2026-07-21","cited_by_count":1,"area":"safety"},{"id":"2607.27081","title":"On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2506.11253","title":"Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models","created":"2025-06-12","cited_by_count":0,"area":"safety"},{"id":"2507.04106","title":"Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning","created":"2025-07-05","cited_by_count":0,"area":"safety"},{"id":"2509.23381","title":"Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT","created":"2025-09-27","cited_by_count":0,"area":"safety"},{"id":"2511.18660","title":"Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2601.06938","title":"Forgetting Similar Samples: Can Machine Unlearning Do it Better?","created":"2026-01-11","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":"2602.02139","title":"EvoMU: Evolutionary Machine Unlearning","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.06887","title":"Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2602.19215","title":"Understanding Empirical Unlearning with Combinatorial Interpretability","created":"2026-02-22","cited_by_count":0,"area":"safety"},{"id":"2602.23798","title":"MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models","created":"2026-02-27","cited_by_count":0,"area":"safety"},{"id":"2604.05716","title":"Can Large Language Models Reinvent Foundational Algorithms?","created":"2026-04-07","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}