{"total":26,"rows":[{"id":"2410.07163","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","created":"2024-10-09","cited_by_count":172,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2502.19301","title":"Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond","created":"2025-02-26","cited_by_count":61,"area":"lr"},{"id":"2502.14829","title":"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps","created":"2025-02-20","cited_by_count":47,"area":"lr"},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2410.17050","title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","created":"2024-10-22","cited_by_count":15,"area":"lr"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2512.22255","title":"Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks","created":"2025-12-24","cited_by_count":11,"area":"lr"},{"id":"2509.24156","title":"Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2511.05784","title":"DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning","created":"2025-11-08","cited_by_count":7,"area":"lr"},{"id":"2605.18891","title":"Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2506.17279","title":"Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models","created":"2025-06-14","cited_by_count":6,"area":"lr"},{"id":"2504.11364","title":"Offline Learning and Forgetting for Reasoning with Large Language Models","created":"2025-04-15","cited_by_count":4,"area":"lr"},{"id":"2512.17911","title":"Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2601.09281","title":"STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2506.02541","title":"Rethinking Post-Unlearning Behavior of Large Vision-Language Models","created":"2025-06-03","cited_by_count":0,"area":"lr"},{"id":"2512.19728","title":"Hard Negative Sample-Augmented DPO Post-Training for Small Language Models","created":"2025-12-17","cited_by_count":0,"area":"lr"},{"id":"2605.14636","title":"Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2608.04519","title":"Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.11691","title":"LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.17804","title":"An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2609.34442","title":"Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.12769","title":"REDaCT: Collapse-Free Unlearning in Large Reasoning Models","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}