{"total":16,"rows":[{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2502.09674","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions","created":"2025-02-13","cited_by_count":41,"area":"lr"},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2506.00772","title":"LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2501.19180","title":"Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning","created":"2025-01-31","cited_by_count":11,"area":"lr"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2507.17075","title":"LoRA is All You Need for Safety Alignment of Reasoning LLMs","created":"2025-07-22","cited_by_count":6,"area":"lr"},{"id":"2602.21346","title":"Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment","created":"2026-02-24","cited_by_count":2,"area":"lr"},{"id":"2604.00012","title":"Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2602.04224","title":"RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2604.09750","title":"Conflicts Make Large Reasoning Models Vulnerable to Attacks","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2511.12155","title":"Rethinking Deep Alignment Through The Lens Of Incomplete Learning","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2604.04120","title":"Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression","created":"2026-04-05","cited_by_count":0,"area":"lr"},{"id":"2607.28146","title":"Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game","created":"2026-07-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}