{"total":89,"rows":[{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"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":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"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":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"area":"safety"},{"id":"2406.11614","title":"Intrinsic Test of Unlearning Using Parametric Knowledge Traces","created":"2024-06-17","cited_by_count":29,"area":"safety"},{"id":"2407.01920","title":"To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models","created":"2024-07-02","cited_by_count":26,"area":"safety"},{"id":"2410.06606","title":"Dissecting Fine-Tuning Unlearning in Large Language Models","created":"2024-10-09","cited_by_count":26,"area":"safety"},{"id":"2406.10952","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","created":"2024-06-16","cited_by_count":24,"area":"safety"},{"id":"2407.20224","title":"Can Editing LLMs Inject Harm?","created":"2024-07-29","cited_by_count":22,"area":"safety"},{"id":"2411.02631","title":"Extracting Unlearned Information from LLMs with Activation Steering","created":"2024-11-04","cited_by_count":21,"area":"safety"},{"id":"2405.20778","title":"Improved Generation of Adversarial Examples Against Safety-aligned LLMs","created":"2024-05-28","cited_by_count":18,"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":"2410.15153","title":"Evaluating Deep Unlearning in Large Language Models","created":"2024-10-19","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":"2406.09325","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":"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":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2502.15826","title":"CoME: An Unlearning-based Approach to Conflict-free Model Editing","created":"2025-02-20","cited_by_count":12,"area":"safety"},{"id":"2508.13650","title":"CRISP: Persistent Concept Unlearning via Sparse Autoencoders","created":"2025-08-19","cited_by_count":11,"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":"2505.16252","title":"Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models","created":"2025-05-22","cited_by_count":10,"area":"safety"},{"id":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","cited_by_count":9,"area":"safety"},{"id":"2408.10722","title":"MEGen: Generative Backdoor into Large Language Models via Model Editing","created":"2024-08-20","cited_by_count":8,"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":"2502.15082","title":"UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning","created":"2025-02-20","cited_by_count":7,"area":"safety"},{"id":"2505.23270","title":"Does Machine Unlearning Truly Remove Knowledge?","created":"2025-05-29","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":"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":"2411.18280","title":"Neutralizing Backdoors through Information Conflicts for Large Language Models","created":"2024-11-27","cited_by_count":5,"area":"safety"},{"id":"2505.15674","title":"UniErase: Towards Balanced and Precise Unlearning in Language Models","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2505.22298","title":"Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing","created":"2025-05-28","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":"2410.21750","title":"Learning and Unlearning of Fabricated Knowledge in Language Models","created":"2024-10-29","cited_by_count":4,"area":"safety"},{"id":"2411.04388","title":"Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method","created":"2024-11-07","cited_by_count":4,"area":"safety"},{"id":"2508.15182","title":"SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks","created":"2025-08-21","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":"2511.18684","title":"Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation","created":"2025-11-24","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":"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":"2604.15166","title":"Class Unlearning via Depth-Aware Removal of Forget-Specific Directions","created":"2026-04-16","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":"2506.07795","title":"LLM Unlearning Should Be Form-Independent","created":"2025-06-09","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":"2408.05330","title":"Neural Machine Unranking","created":"2024-08-09","cited_by_count":2,"area":"safety"},{"id":"2411.00204","title":"RESTOR: Knowledge Recovery in Machine Unlearning","created":"2024-10-31","cited_by_count":2,"area":"safety"},{"id":"2502.15836","title":"Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models","created":"2025-02-20","cited_by_count":2,"area":"safety"},{"id":"2508.17681","title":"Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery","created":"2025-08-25","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":"2602.22562","title":"Layer-Targeted Multilingual Knowledge Erasure in Large Language Models","created":"2026-02-26","cited_by_count":2,"area":"safety"},{"id":"2605.03058","title":"Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation","created":"2026-05-04","cited_by_count":2,"area":"safety"},{"id":"2607.00605","title":"Auditing Forgetting in Limited Memory Language Models","created":"2026-07-01","cited_by_count":2,"area":"safety"},{"id":"2607.02513","title":"LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning","created":"2026-07-02","cited_by_count":2,"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":"2509.15621","title":"Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets","created":"2025-09-19","cited_by_count":1,"area":"safety"},{"id":"2509.20230","title":"Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization","created":"2025-09-24","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":"2512.07374","title":"Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning","created":"2025-12-08","cited_by_count":1,"area":"safety"},{"id":"2603.12275","title":"GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping","created":"2026-02-21","cited_by_count":1,"area":"safety"},{"id":"2605.15138","title":"Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution","created":"2026-05-14","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":"2608.05783","title":"GROM: Gradient-Free Rapid One-Shot Machine Unlearning","created":"2026-08-06","cited_by_count":1,"area":"safety"},{"id":"2504.12996","title":"SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation","created":"2025-04-17","cited_by_count":0,"area":"safety"},{"id":"2510.07822","title":"SIMU: Selective Influence Machine Unlearning","created":"2025-10-09","cited_by_count":0,"area":"safety"},{"id":"2512.04457","title":"RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning","created":"2025-12-04","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":"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":"2602.17696","title":"Can LLM Safety Be Ensured by Constraining Parameter Regions?","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2605.01047","title":"LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.01699","title":"Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance","created":"2026-05-03","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":"2605.30514","title":"MAAT: Multi-phase Adapter-Aware Targeted Unlearning","created":"2026-05-28","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":"2606.13461","title":"Reinforcement Learning for Neural Model Editing","created":"2026-06-11","cited_by_count":0,"area":"safety"},{"id":"2606.18309","title":"SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector","created":"2026-06-16","cited_by_count":0,"area":"safety"},{"id":"2606.19222","title":"Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning","created":"2026-06-17","cited_by_count":0,"area":"safety"},{"id":"2606.30899","title":"Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models","created":"2026-06-29","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":"2608.01422","title":"QR-Erase: Efficient Subspace-Based Machine Unlearning with Layer Localization","created":"2026-08-02","cited_by_count":0,"area":"safety"},{"id":"2609.05794","title":"Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks","created":"2026-09-05","cited_by_count":0,"area":"safety"},{"id":"2609.29045","title":"The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning","created":"2026-09-24","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":"2609.39866","title":"Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2609.39882","title":"LLM Persona Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.00348","title":"Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation","created":"2026-09-29","cited_by_count":0,"area":"safety"}],"next_cursor":null}