{"total":33,"rows":[{"id":"2507.05246","title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors","created":"2025-07-07","cited_by_count":88,"area":"lr"},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2509.02350","title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","created":"2025-09-02","cited_by_count":43,"area":"lr"},{"id":"2510.19851","title":"Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability","created":"2025-10-21","cited_by_count":22,"area":"lr"},{"id":"2506.22777","title":"Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning","created":"2025-06-28","cited_by_count":21,"area":"lr"},{"id":"2507.12428","title":"Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models","created":"2025-07-16","cited_by_count":17,"area":"lr"},{"id":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17,"area":"lr"},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2510.23966","title":"A Pragmatic Way to Measure Chain-of-Thought Monitorability","created":"2025-10-28","cited_by_count":13,"area":"lr"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"area":"lr"},{"id":"2512.00218","title":"Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2510.09714","title":"All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2601.23086","title":"Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2605.18549","title":"Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2510.01069","title":"Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning","created":"2025-10-01","cited_by_count":3,"area":"lr"},{"id":"2606.20560","title":"How Transparent is DiffusionGemma?","created":"2026-06-18","cited_by_count":3,"area":"lr"},{"id":"2510.19476","title":"A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2602.13904","title":"Diagnosing Pathological Chain-of-Thought in Reasoning Models","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2608.04735","title":"Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2509.21465","title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2603.05618","title":"Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2607.09786","title":"Length Penalties Make Chain-of-Thought Less Monitorable","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2602.04856","title":"CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2603.21376","title":"A transformer architecture alteration to incentivise externalised reasoning","created":"2026-03-22","cited_by_count":0,"area":"lr"},{"id":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2608.00583","title":"A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility","created":"2026-08-01","cited_by_count":0,"area":"lr"},{"id":"2609.02754","title":"Untangling the Mechanisms of Misleading Context in Medical Question Answering","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.31121","title":"Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.35074","title":"When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.39838","title":"Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.04914","title":"Monitorability Disposition in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}