{"total":19,"rows":[{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170,"area":"lr"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"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":"2502.09673","title":"Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning","created":"2025-02-13","cited_by_count":20,"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":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"id":"2408.08651","title":"Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow","created":"2024-08-16","cited_by_count":8,"area":"lr"},{"id":"2510.09555","title":"A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2603.16643","title":"Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy","created":"2026-03-17","cited_by_count":8,"area":"lr"},{"id":"2603.01437","title":"Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2504.05632","title":"Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning","created":"2025-04-08","cited_by_count":5,"area":"lr"},{"id":"2602.14469","title":"Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2608.16747","title":"Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2510.09278","title":"CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2608.05188","title":"Position: It's Time to Optimize LLMs for Self-Consistency","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2608.29464","title":"Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered","created":"2026-08-29","cited_by_count":1,"area":"lr"},{"id":"2605.28467","title":"Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2608.25379","title":"Adaptive Triggering for Bias Correction in LLM Reasoning","created":"2026-08-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}