{"total":35,"rows":[{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2310.20150","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","created":"2023-10-31","cited_by_count":215,"area":"safety"},{"id":"2403.13355","title":"BadEdit: Backdooring large language models by model editing","created":"2024-03-20","cited_by_count":96,"area":"safety"},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2307.03941","title":"Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions","created":"2023-07-08","cited_by_count":60,"area":"safety"},{"id":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33,"area":"safety"},{"id":"2405.16720","title":"Large Scale Knowledge Washing","created":"2024-05-26","cited_by_count":16,"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":"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":"2505.19855","title":"Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?","created":"2025-05-26","cited_by_count":13,"area":"safety"},{"id":"2310.02164","title":"A Survey of Graph Unlearning","created":"2023-08-23","cited_by_count":12,"area":"safety"},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2502.11647","title":"DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing","created":"2025-02-17","cited_by_count":10,"area":"safety"},{"id":"2502.15082","title":"UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning","created":"2025-02-20","cited_by_count":7,"area":"safety"},{"id":"2409.13054","title":"LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models","created":"2024-09-19","cited_by_count":5,"area":"safety"},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2510.16367","title":"EditMark: Watermarking Large Language Models based on Model Editing","created":"2025-10-18","cited_by_count":4,"area":"safety"},{"id":"2512.20794","title":"Investigating Model Editing for Unlearning in Large Language Models","created":"2025-12-23","cited_by_count":4,"area":"safety"},{"id":"2504.12681","title":"GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs","created":"2025-04-17","cited_by_count":3,"area":"safety"},{"id":"2510.02392","title":"KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning","created":"2025-10-01","cited_by_count":3,"area":"safety"},{"id":"2406.03603","title":"MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation","created":"2024-06-05","cited_by_count":1,"area":"safety"},{"id":"2511.19566","title":"ModHiFi: Identifying High Fidelity predictive components for Model Modification","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2512.10348","title":"REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature","created":"2025-12-11","cited_by_count":1,"area":"safety"},{"id":"2602.02595","title":"To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack","created":"2026-02-01","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":"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":"2601.08840","title":"Consistency-Aware Editing for Entity-level Unlearning in Language Models","created":"2025-12-19","cited_by_count":0,"area":"safety"},{"id":"2604.17384","title":"Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion","created":"2026-04-19","cited_by_count":0,"area":"safety"},{"id":"2605.18879","title":"ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2606.10989","title":"Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning","created":"2026-06-09","cited_by_count":0,"area":"safety"},{"id":"2607.16227","title":"LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2609.32434","title":"From Latents to Wires: Surgical Post-Editing on Large Language Models","created":"2026-09-26","cited_by_count":0,"area":"safety"},{"id":"2609.37858","title":"Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.39882","title":"LLM Persona Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}