{"total":40,"rows":[{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032,"area":"safety"},{"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":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"area":"safety"},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224,"area":"safety"},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"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":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96,"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":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"area":"safety"},{"id":"2406.17216","title":"Machine Unlearning Fails to Remove Data Poisoning Attacks","created":"2024-06-25","cited_by_count":37,"area":"safety"},{"id":"2406.12329","title":"Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport","created":"2024-06-18","cited_by_count":10,"area":"safety"},{"id":"2406.14091","title":"Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models","created":"2024-06-20","cited_by_count":10,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2507.15112","title":"Distributional Machine Unlearning via Selective Data Removal","created":"2025-07-20","cited_by_count":5,"area":"safety"},{"id":"2508.06595","title":"LLM Unlearning Without an Expert Curated Dataset","created":"2025-08-08","cited_by_count":5,"area":"safety"},{"id":"2507.11128","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2510.25117","title":"A Survey on Unlearning in Large Language Models","created":"2025-10-29","cited_by_count":4,"area":"safety"},{"id":"2601.22359","title":"The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples","created":"2026-01-29","cited_by_count":4,"area":"safety"},{"id":"2603.22061","title":"On the Failure of Topic-Matched Contrast Baselines in Multi-Directional Refusal Abliteration","created":"2026-03-23","cited_by_count":3,"area":"safety"},{"id":"2411.00204","title":"RESTOR: Knowledge Recovery in Machine Unlearning","created":"2024-10-31","cited_by_count":2,"area":"safety"},{"id":"2506.20941","title":"Revisiting the Past: Data Unlearning with Model State History","created":"2025-06-26","cited_by_count":2,"area":"safety"},{"id":"2601.21564","title":"Representation Unlearning: Forgetting through Information Compression","created":"2026-01-29","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":"2605.16645","title":"Statistical Unlearning of Distributions: A Hypothesis Testing Approach","created":"2026-05-15","cited_by_count":1,"area":"safety"},{"id":"2505.18672","title":"Concept Concentration for Faithful Representation Intervention","created":"2025-05-24","cited_by_count":0,"area":"safety"},{"id":"2509.16525","title":"CAF\\'E: Causal Black-Box Testing of Machine Unlearning","created":"2025-09-20","cited_by_count":0,"area":"safety"},{"id":"2510.12672","title":"Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers","created":"2025-10-14","cited_by_count":0,"area":"safety"},{"id":"2511.23174","title":"Are LLMs Good Safety Agents or a Propaganda Engine?","created":"2025-11-28","cited_by_count":0,"area":"safety"},{"id":"2604.08111","title":"Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?","created":"2026-04-09","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":"2607.03932","title":"MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs","created":"2026-07-04","cited_by_count":0,"area":"safety"},{"id":"2608.13478","title":"MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning","created":"2026-08-13","cited_by_count":0,"area":"safety"},{"id":"2609.00445","title":"Capability-Gated Language Models: Security Composes, Utility Does Not","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.14861","title":"Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete Representations","created":"2026-09-14","cited_by_count":0,"area":"safety"},{"id":"2609.38895","title":"Unmerge: Efficient Machine Unlearning via Task Arithmetic","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2609.38929","title":"Learning What to Forget: Distributional Unlearning for LLM Representation Spaces","created":"2026-09-30","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}