{"total":24,"rows":[{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","cited_by_count":88,"area":"safety"},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2402.05813","title":"Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models","created":"2024-02-08","cited_by_count":39,"area":"safety"},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"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":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2406.11780","title":"Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs","created":"2024-06-17","cited_by_count":18,"area":"safety"},{"id":"2504.17480","title":"Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation","created":"2025-04-24","cited_by_count":11,"area":"safety"},{"id":"2403.14725","title":"Testing the Limits of Jailbreaking Defenses with the Purple Problem","created":"2024-03-20","cited_by_count":8,"area":"safety"},{"id":"2507.19894","title":"Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols","created":"2025-07-26","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":"2404.19048","title":"A Framework for Real-time Safeguarding the Text Generation of Large Language Model","created":"2024-04-29","cited_by_count":2,"area":"safety"},{"id":"2605.31293","title":"Divergence Decoding: Inference-Time Unlearning via Auxiliary Models","created":"2026-05-29","cited_by_count":2,"area":"safety"},{"id":"2504.01533","title":"LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution","created":"2025-04-02","cited_by_count":1,"area":"safety"},{"id":"2601.06938","title":"Forgetting Similar Samples: Can Machine Unlearning Do it Better?","created":"2026-01-11","cited_by_count":0,"area":"safety"},{"id":"2603.07452","title":"Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs","created":"2026-03-08","cited_by_count":0,"area":"safety"},{"id":"2605.19940","title":"Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2605.27997","title":"Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models","created":"2026-05-27","cited_by_count":0,"area":"safety"},{"id":"2606.25380","title":"A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2609.16229","title":"Test-Time Unlearning via Sparse Autoencoder","created":"2026-09-14","cited_by_count":0,"area":"safety"},{"id":"2610.18359","title":"Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}