{"total":302,"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":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504,"area":"alignment"},{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"area":"safety"},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"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":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"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":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","cited_by_count":88,"area":"safety"},{"id":"2406.13356","title":"Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning","created":"2024-06-19","cited_by_count":84,"area":"safety"},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2502.05374","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","created":"2025-02-07","cited_by_count":79,"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":"2404.12038","title":"Uncovering Safety Risks of Large Language Models through Concept Activation Vector","created":"2024-04-18","cited_by_count":67,"area":"alignment"},{"id":"2502.19301","title":"Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond","created":"2025-02-26","cited_by_count":61,"area":"lr"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2410.08109","title":"A Closer Look at Machine Unlearning for Large Language Models","created":"2024-10-10","cited_by_count":56,"area":"safety"},{"id":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"area":"safety"},{"id":"2404.05880","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","created":"2024-04-08","cited_by_count":51,"area":"safety"},{"id":"2406.09324","title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","created":"2024-06-13","cited_by_count":51,"area":"safety"},{"id":"2407.00106","title":"UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI","created":"2024-06-27","cited_by_count":51,"area":"safety"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2410.12855","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","created":"2024-10-11","cited_by_count":47,"area":"agents"},{"id":"2405.12523","title":"Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models","created":"2024-05-21","cited_by_count":46,"area":"mllm"},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"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":"2410.12777","title":"Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts","created":"2024-10-16","cited_by_count":40,"area":"diffusion"},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39,"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":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38,"area":null},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"area":"safety"},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2405.07406","title":"Machine Unlearning: A Comprehensive Survey","created":"2024-05-13","cited_by_count":35,"area":"safety"},{"id":"2402.00751","title":"Fast Exact Unlearning for In-Context Learning Data for LLMs","created":"2024-02-01","cited_by_count":34,"area":"safety"},{"id":"2410.02760","title":"Erasing Conceptual Knowledge from Language Models","created":"2024-10-03","cited_by_count":34,"area":"safety"},{"id":"2403.16257","title":"Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning","created":"2024-03-24","cited_by_count":31,"area":"safety"},{"id":"2411.03554","title":"Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset","created":"2024-11-05","cited_by_count":30,"area":"mllm"},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2407.02855","title":"From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks","created":"2024-07-03","cited_by_count":29,"area":"safety"},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2406.09179","title":"Towards Effective Evaluations and Comparisons for LLM Unlearning Methods","created":"2024-06-13","cited_by_count":27,"area":"safety"},{"id":"2406.06622","title":"Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs","created":"2024-06-07","cited_by_count":26,"area":"safety"},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2410.15267","title":"When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?","created":"2024-10-20","cited_by_count":24,"area":"rag"},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2403.08743","title":"Prompting Fairness: Integrating Causality to Debias Large Language Models","created":"2024-03-13","cited_by_count":21,"area":null},{"id":"2506.01339","title":"Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning","created":"2025-06-02","cited_by_count":21,"area":"safety"},{"id":"2412.06681","title":"Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework","created":"2024-12-09","cited_by_count":19,"area":"agents"},{"id":"2503.06339","title":"Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning","created":"2025-03-08","cited_by_count":19,"area":"safety"},{"id":"2410.23232","title":"Attribute-to-Delete: Machine Unlearning via Datamodel Matching","created":"2024-10-30","cited_by_count":18,"area":"safety"},{"id":"2412.06370","title":"Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2505.24428","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections","created":"2025-05-30","cited_by_count":18,"area":"safety"},{"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":"2404.16841","title":"Machine Unlearning in Large Language Models","created":"2024-02-03","cited_by_count":17,"area":"safety"},{"id":"2405.13820","title":"Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching","created":"2024-05-22","cited_by_count":17,"area":"alignment"},{"id":"2502.01083","title":"Tool Unlearning for Tool-Augmented LLMs","created":"2025-02-03","cited_by_count":17,"area":"agents"},{"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":"2510.19422","title":"LLM Unlearning with LLM Beliefs","created":"2025-10-22","cited_by_count":17,"area":"safety"},{"id":"2510.21189","title":"Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency","created":"2025-10-24","cited_by_count":17,"area":"safety"},{"id":"2403.03536","title":"Towards Efficient and Effective Unlearning of Large Language Models for Recommendation","created":"2024-03-06","cited_by_count":16,"area":"safety"},{"id":"2405.16720","title":"Large Scale Knowledge Washing","created":"2024-05-26","cited_by_count":16,"area":"safety"},{"id":"2406.14928","title":"Autonomous Agents for Collaborative Task under Information Asymmetry","created":"2024-06-21","cited_by_count":16,"area":"agents"},{"id":"2503.11832","title":"Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning","created":"2025-03-14","cited_by_count":16,"area":"mllm"},{"id":"2408.13808","title":"Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models","created":"2024-08-25","cited_by_count":15,"area":null},{"id":"2410.17050","title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","created":"2024-10-22","cited_by_count":15,"area":"lr"},{"id":"2412.06966","title":"Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research","created":"2024-12-09","cited_by_count":15,"area":"safety"},{"id":"2410.15153","title":"Evaluating Deep Unlearning in Large Language Models","created":"2024-10-19","cited_by_count":14,"area":"safety"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2406.09325","title":"REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space","created":"2024-06-13","cited_by_count":13,"area":"safety"},{"id":"2503.14530","title":"SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders","created":"2025-03-16","cited_by_count":13,"area":"mllm"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2406.08288","title":"Decoupling the Class Label and the Target Concept in Machine Unlearning","created":"2024-06-12","cited_by_count":12,"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":"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":"2404.17733","title":"Building a Large Japanese Web Corpus for Large Language Models","created":"2024-04-27","cited_by_count":11,"area":null},{"id":"2405.17462","title":"Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity","created":"2024-05-23","cited_by_count":11,"area":"safety"},{"id":"2504.12574","title":"ForgetMe: Evaluating Selective Forgetting in Generative Models","created":"2025-04-17","cited_by_count":11,"area":"diffusion"},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2506.06112","title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"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":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2402.08078","title":"Large Language Models as Agents in Two-Player Games","created":"2024-02-12","cited_by_count":10,"area":"agents"},{"id":"2502.17591","title":"Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2506.05314","title":"Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2506.00359","title":"Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy","created":"2025-05-31","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":"2511.04934","title":"Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding","created":"2025-11-07","cited_by_count":9,"area":"safety"}],"next_cursor":"100"}