{"total":312,"rows":[{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504,"area":"alignment"},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2310.02238","title":"Who's Harry Potter? Approximate Unlearning in LLMs","created":"2023-10-03","cited_by_count":381,"area":"safety"},{"id":"2405.14831","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","created":"2024-05-23","cited_by_count":281,"area":"rag"},{"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":"2304.04934","title":"Model Sparsity Can Simplify Machine Unlearning","created":"2023-04-11","cited_by_count":214,"area":"safety"},{"id":"2310.11868","title":"To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now","created":"2023-10-18","cited_by_count":210,"area":"diffusion"},{"id":"2308.07707","title":"Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening","created":"2023-08-15","cited_by_count":181,"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":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2405.15234","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","created":"2024-05-24","cited_by_count":168,"area":"diffusion"},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2308.07061","title":"Machine Unlearning: Solutions and Challenges","created":"2023-08-14","cited_by_count":93,"area":"safety"},{"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":"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":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73,"area":"safety"},{"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":"2411.09523","title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","created":"2024-11-14","cited_by_count":65,"area":"agents"},{"id":"2310.20448","title":"A Survey on Federated Unlearning: Challenges, Methods, and Future Directions","created":"2023-10-31","cited_by_count":63,"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":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55,"area":"safety"},{"id":"2401.06187","title":"Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks","created":"2024-01-11","cited_by_count":52,"area":"safety"},{"id":"2305.06360","title":"Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy","created":"2023-05-10","cited_by_count":51,"area":"safety"},{"id":"2402.11846","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","created":"2024-02-19","cited_by_count":50,"area":"diffusion"},{"id":"2406.09073","title":"Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition","created":"2024-06-13","cited_by_count":50,"area":"safety"},{"id":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","cited_by_count":47,"area":"safety"},{"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":"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":"2309.13876","title":"Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data","created":"2023-09-25","cited_by_count":42,"area":null},{"id":"2403.01267","title":"Dissecting Language Models: Machine Unlearning via Selective Pruning","created":"2024-03-02","cited_by_count":42,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39,"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":"2212.09573","title":"Privacy Adhering Machine Un-learning in NLP","created":"2022-12-19","cited_by_count":36,"area":"safety"},{"id":"2405.07406","title":"Machine Unlearning: A Comprehensive Survey","created":"2024-05-13","cited_by_count":35,"area":"safety"},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2210.08196","title":"Deep Regression Unlearning","created":"2022-10-15","cited_by_count":32,"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":"2408.00920","title":"Towards Certified Unlearning for Deep Neural Networks","created":"2024-08-01","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":"2403.11530","title":"Continual Forgetting for Pre-trained Vision Models","created":"2024-03-18","cited_by_count":29,"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":"2503.23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks","created":"2025-03-31","cited_by_count":28,"area":"safety"},{"id":"2401.05146","title":"Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics","created":"2024-01-10","cited_by_count":27,"area":"safety"},{"id":"2406.16257","title":"Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning","created":"2024-06-24","cited_by_count":27,"area":"safety"},{"id":"2506.06985","title":"Certified Unlearning for Neural Networks","created":"2025-06-08","cited_by_count":27,"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":"2306.02174","title":"Training Data Attribution for Diffusion Models","created":"2023-06-03","cited_by_count":24,"area":"diffusion"},{"id":"2409.11219","title":"Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models","created":"2024-09-17","cited_by_count":23,"area":"diffusion"},{"id":"2401.07348","title":"Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity","created":"2024-01-14","cited_by_count":21,"area":null},{"id":"2408.00929","title":"Verification of Machine Unlearning is Fragile","created":"2024-08-01","cited_by_count":21,"area":"safety"},{"id":"2412.09119","title":"The Utility and Complexity of in- and out-of-Distribution Machine Unlearning","created":"2024-12-12","cited_by_count":20,"area":"safety"},{"id":"2306.03558","title":"Machine Unlearning: A Survey","created":"2023-06-06","cited_by_count":19,"area":"safety"},{"id":"2409.09778","title":"Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions","created":"2024-09-15","cited_by_count":19,"area":"safety"},{"id":"2504.09039","title":"Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization","created":"2025-04-12","cited_by_count":19,"area":"diffusion"},{"id":"2309.00886","title":"Tight Bounds for Machine Unlearning via Differential Privacy","created":"2023-09-02","cited_by_count":18,"area":"safety"},{"id":"2404.00506","title":"Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models","created":"2024-03-31","cited_by_count":18,"area":"safety"},{"id":"2404.12922","title":"Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images","created":"2024-04-19","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":"2503.06991","title":"Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols","created":"2025-03-10","cited_by_count":18,"area":"safety"},{"id":"2404.16841","title":"Machine Unlearning in Large Language Models","created":"2024-02-03","cited_by_count":17,"area":"safety"},{"id":"2303.05699","title":"Feature Unlearning for Pre-trained GANs and VAEs","created":"2023-03-10","cited_by_count":16,"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":"2406.07687","title":"Adversarial Machine Unlearning","created":"2024-06-11","cited_by_count":16,"area":"safety"},{"id":"2210.11334","title":"Proof of Unlearning: Definitions and Instantiation","created":"2022-10-20","cited_by_count":15,"area":"safety"},{"id":"2310.05847","title":"Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems","created":"2023-10-06","cited_by_count":15,"area":"safety"},{"id":"2402.05355","title":"A Survey on Safe Multi-Modal Learning System","created":"2024-02-08","cited_by_count":15,"area":null},{"id":"2410.08074","title":"Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models","created":"2024-10-10","cited_by_count":15,"area":"diffusion"},{"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":"2304.10638","title":"Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning","created":"2023-04-20","cited_by_count":13,"area":null},{"id":"2309.16173","title":"Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation","created":"2023-09-28","cited_by_count":13,"area":"safety"},{"id":"2312.02052","title":"DUCK: Distance-based Unlearning via Centroid Kinematics","created":"2023-12-04","cited_by_count":13,"area":"safety"},{"id":"2404.19382","title":"Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective","created":"2024-04-30","cited_by_count":13,"area":"diffusion"},{"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":"2310.02164","title":"A Survey of Graph Unlearning","created":"2023-08-23","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":"2503.13917","title":"Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels","created":"2025-03-18","cited_by_count":12,"area":"safety"},{"id":"2308.09881","title":"Generative Adversarial Networks Unlearning","created":"2023-08-19","cited_by_count":11,"area":"safety"},{"id":"2309.14054","title":"Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networks","created":"2023-09-25","cited_by_count":11,"area":"safety"},{"id":"2403.14339","title":"$\\nabla \\tau$: Gradient-based and Task-Agnostic machine Unlearning","created":"2024-03-21","cited_by_count":11,"area":"safety"},{"id":"2405.17462","title":"Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity","created":"2024-05-23","cited_by_count":11,"area":"safety"},{"id":"2405.17878","title":"An Information Theoretic Evaluation Metric For Strong Unlearning","created":"2024-05-28","cited_by_count":11,"area":"safety"},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2506.14003","title":"Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs","created":"2025-06-16","cited_by_count":11,"area":"safety"},{"id":"2311.15268","title":"Unlearning via Sparse Representations","created":"2023-11-26","cited_by_count":10,"area":"safety"},{"id":"2312.07420","title":"FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs","created":"2023-12-12","cited_by_count":10,"area":"safety"},{"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":"2302.09813","title":"Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare","created":"2023-02-20","cited_by_count":9,"area":null},{"id":"2405.19211","title":"Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning","created":"2024-05-29","cited_by_count":9,"area":"safety"},{"id":"2406.07698","title":"Label Smoothing Improves Machine Unlearning","created":"2024-06-11","cited_by_count":9,"area":"safety"},{"id":"2410.01276","title":"Deep Unlearn: Benchmarking Machine Unlearning for Image Classification","created":"2024-10-02","cited_by_count":9,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","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"}],"next_cursor":"100"}