{"total":79,"rows":[{"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":"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":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"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":"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":"2403.13355","title":"BadEdit: Backdooring large language models by model editing","created":"2024-03-20","cited_by_count":96,"area":"safety"},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79,"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":"2410.11143","title":"LLM Unlearning via Loss Adjustment with Only Forget Data","created":"2024-10-14","cited_by_count":75,"area":"safety"},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"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":"2406.18664","title":"Evaluating Copyright Takedown Methods for Language Models","created":"2024-06-26","cited_by_count":43,"area":null},{"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":"2406.18406","title":"IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons","created":"2024-06-26","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":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34,"area":null},{"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":"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":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2411.02631","title":"Extracting Unlearned Information from LLMs with Activation Steering","created":"2024-11-04","cited_by_count":21,"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":"2506.07171","title":"RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality","created":"2025-06-08","cited_by_count":16,"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":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","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":"2506.14003","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":"2402.18099","title":"Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models","created":"2024-02-28","cited_by_count":10,"area":null},{"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":"2510.04217","title":"MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering","created":"2025-10-05","cited_by_count":10,"area":"mllm"},{"id":"2403.15230","title":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2406.15386","title":"U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI","created":"2024-04-22","cited_by_count":7,"area":null},{"id":"2410.06704","title":"PII-Scope: A Comprehensive Study on Training Data PII Extraction Attacks in LLMs","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2509.20977","title":"CLUE: Conflict-guided Localization for LLM Unlearning Framework","created":"2025-09-25","cited_by_count":7,"area":"safety"},{"id":"2511.05784","title":"DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning","created":"2025-11-08","cited_by_count":7,"area":"lr"},{"id":"2504.14452","title":"ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data","created":"2025-04-20","cited_by_count":6,"area":"alignment"},{"id":"2506.17279","title":"Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models","created":"2025-06-14","cited_by_count":6,"area":"lr"},{"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":"2502.19982","title":"Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models","created":"2025-02-27","cited_by_count":5,"area":"safety"},{"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":"2408.04983","title":"Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2411.01948","title":"Learning Where to Edit Vision Transformers","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2506.12484","title":"Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization","created":"2025-06-14","cited_by_count":4,"area":"safety"},{"id":"2510.00761","title":"Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2605.06076","title":"Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training","created":"2026-05-07","cited_by_count":4,"area":"mechinterp"},{"id":"2505.04578","title":"Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization","created":"2025-05-07","cited_by_count":3,"area":"safety"},{"id":"2506.05647","title":"Learning to Weight Parameters for Training Data Attribution","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2509.11816","title":"Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning","created":"2025-09-15","cited_by_count":3,"area":"safety"},{"id":"2510.04773","title":"Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning","created":"2025-10-06","cited_by_count":3,"area":"alignment"},{"id":"2512.08946","title":"Large Language Models as Search Engines: Societal Challenges","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2404.05047","title":"Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2508.01324","title":"Towards Evaluation for Real-World LLM Unlearning","created":"2025-08-02","cited_by_count":2,"area":"safety"},{"id":"2510.07626","title":"LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics","created":"2025-10-08","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":"2602.19275","title":"KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models","created":"2026-02-22","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":"2504.00031","title":"Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2506.15076","title":"Learning-Time Encoding Shapes Unlearning in LLMs","created":"2025-06-18","cited_by_count":1,"area":"safety"},{"id":"2508.10065","title":"Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2511.11914","title":"Forgetting-MarI: LLM Unlearning via Marginal Information Regularization","created":"2025-11-14","cited_by_count":1,"area":"safety"},{"id":"2601.21702","title":"Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities","created":"2026-01-29","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":"2405.00704","title":"A Survey on the Real Power of ChatGPT","created":"2024-04-22","cited_by_count":0,"area":null},{"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":"2601.16905","title":"GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints","created":"2026-01-23","cited_by_count":0,"area":"moe"},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.09559","title":"Safe-RULE: Safe Reinforcement UnLEarning","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2609.00492","title":"The Privacy-Hallucination Tradeoff in Differentially Private Language Models","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.40286","title":"Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.14763","title":"CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation","created":"2026-10-10","cited_by_count":0,"area":"mllm"}],"next_cursor":null}