{"total":17,"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":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"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":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2509.25673","title":"Mitigating Biases in Language Models via Bias Unlearning","created":"2025-09-30","cited_by_count":6,"area":"safety"},{"id":"2507.15112","title":"Distributional Machine Unlearning via Selective Data Removal","created":"2025-07-20","cited_by_count":5,"area":"safety"},{"id":"2407.16951","title":"Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation","created":"2024-07-24","cited_by_count":4,"area":"safety"},{"id":"2512.14137","title":"Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Models","created":"2025-12-16","cited_by_count":1,"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":"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":"2608.02058","title":"SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning","created":"2026-08-03","cited_by_count":0,"area":"safety"},{"id":"2608.12652","title":"Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection","created":"2026-08-12","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"}],"next_cursor":null}