{"total":24,"rows":[{"id":"2404.18239","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","created":"2024-04-28","cited_by_count":104,"area":"safety"},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2408.06223","title":"On Effects of Steering Latent Representation for Large Language Model Unlearning","created":"2024-08-12","cited_by_count":32,"area":"safety"},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"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":"2406.09408","title":"Data Attribution for Text-to-Image Models by Unlearning Synthesized Images","created":"2024-06-13","cited_by_count":22,"area":"safety"},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18,"area":"safety"},{"id":"2410.23232","title":"Attribute-to-Delete: Machine Unlearning via Datamodel Matching","created":"2024-10-30","cited_by_count":18,"area":"safety"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2410.01276","title":"Deep Unlearn: Benchmarking Machine Unlearning for Image Classification","created":"2024-10-02","cited_by_count":9,"area":"safety"},{"id":"2406.13551","title":"Mitigating Social Biases in Language Models through Unlearning","created":"2024-06-19","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":"2510.04891","title":"SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests","created":"2025-10-06","cited_by_count":5,"area":"safety"},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","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":"2505.00020","title":"Beyond Public Access in LLM Pre-Training Data","created":"2025-04-24","cited_by_count":3,"area":"safety"},{"id":"2505.16147","title":"Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value","created":"2025-05-22","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":"2604.18970","title":"Mechanistic Anomaly Detection via Functional Attribution","created":"2026-04-21","cited_by_count":1,"area":"safety"},{"id":"2511.21718","title":"When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers","created":"2025-11-19","cited_by_count":0,"area":"safety"},{"id":"2512.05254","title":"When unlearning is free: leveraging low influence points to reduce computational costs","created":"2025-12-04","cited_by_count":0,"area":"safety"},{"id":"2605.27292","title":"Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2609.32103","title":"LLM Unlearning Evaluation with TRIAGE","created":"2026-09-26","cited_by_count":0,"area":"safety"}],"next_cursor":null}