{"total":14,"rows":[{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2601.20568","title":"Reinforcement Unlearning via Group Relative Policy Optimization","created":"2026-01-28","cited_by_count":4,"area":"safety"},{"id":"2603.10913","title":"LLM2Vec-Gen: Generative Embeddings from Large Language Models","created":"2026-03-11","cited_by_count":2,"area":"safety"},{"id":"2508.11925","title":"Optimizing Token Choice for Code Watermarking: An RL Approach","created":"2025-08-16","cited_by_count":1,"area":"safety"},{"id":"2604.18697","title":"Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs","created":"2026-04-20","cited_by_count":1,"area":"safety"},{"id":"2606.11409","title":"Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models","created":"2026-06-09","cited_by_count":1,"area":"safety"},{"id":"2607.27968","title":"Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning","created":"2026-07-30","cited_by_count":1,"area":"safety"},{"id":"2602.19020","title":"Learning to Detect Language Model Training Data via Active Reconstruction","created":"2026-02-22","cited_by_count":0,"area":"safety"},{"id":"2607.20472","title":"Robust Critics: Defending LLMs Against Multi-Turn Attacks","created":"2026-05-24","cited_by_count":0,"area":"safety"},{"id":"2609.26176","title":"Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation","created":"2026-08-12","cited_by_count":0,"area":"safety"},{"id":"2609.33136","title":"Leaky Students: Membership Inference against On-Policy Distillation","created":"2026-09-27","cited_by_count":0,"area":"safety"},{"id":"2609.36121","title":"Render Before Reading: Visual Rendering as a Prompt Injection Defense","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2610.14701","title":"Towards Merging-conditional Backdoor Unalignment against Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"}],"next_cursor":null}