{"total":18,"rows":[{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26,"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":"2509.23392","title":"Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking","created":"2025-09-27","cited_by_count":10,"area":"lr"},{"id":"2603.00131","title":"Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2507.21652","title":"UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases","created":"2025-07-29","cited_by_count":7,"area":"lr"},{"id":"2508.16213","title":"MedOmni-45{\\deg}: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2511.09222","title":"Toward Honest Language Models for Deductive Reasoning","created":"2025-11-12","cited_by_count":3,"area":"lr"},{"id":"2604.08423","title":"Synthetic Data for any Differentiable Target","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2512.07407","title":"Training Language Models to Use Prolog as a Tool","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2601.07180","title":"Structured Reasoning for Large Language Models","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2602.20904","title":"Transcoder Adapters for Reasoning-Model Diffing","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2604.23488","title":"Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation","created":"2026-04-26","cited_by_count":1,"area":"lr"},{"id":"2601.03388","title":"Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models","created":"2026-01-06","cited_by_count":0,"area":"lr"},{"id":"2608.23497","title":"Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.33220","title":"When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34056","title":"Steering Language Model Goals with Value Transplant","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}