{"total":72,"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":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247,"area":"lr"},{"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":"2603.05488","title":"Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought","created":"2026-03-05","cited_by_count":40,"area":"lr"},{"id":"2505.13774","title":"Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models","created":"2025-05-19","cited_by_count":23,"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":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2508.00943","title":"LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring","created":"2025-07-31","cited_by_count":18,"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":"2510.27484","title":"Thought Branches: Interpreting LLM Reasoning Requires Resampling","created":"2025-10-31","cited_by_count":16,"area":"lr"},{"id":"2510.24941","title":"Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought","created":"2025-10-28","cited_by_count":15,"area":"lr"},{"id":"2505.22888","title":"When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy","created":"2025-05-28","cited_by_count":14,"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":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2505.23945","title":"A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models","created":"2025-05-29","cited_by_count":12,"area":"lr"},{"id":"2509.21361","title":"Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs","created":"2025-09-21","cited_by_count":12,"area":null},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2505.19184","title":"When Two LLMs Debate, Both Think They'll Win","created":"2025-05-25","cited_by_count":10,"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":"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":"2508.19827","title":"Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?","created":"2025-08-27","cited_by_count":9,"area":"lr"},{"id":"2510.11196","title":"Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations","created":"2025-10-13","cited_by_count":9,"area":"lr"},{"id":"2510.27338","title":"Reasoning Models Sometimes Output Illegible Chains of Thought","created":"2025-10-31","cited_by_count":9,"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":"2503.01539","title":"Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2602.10117","title":"Biases in the Blind Spot: Detecting What LLMs Fail to Mention","created":"2026-02-10","cited_by_count":8,"area":"lr"},{"id":"2603.05167","title":"C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning","created":"2026-03-05","cited_by_count":7,"area":"lr"},{"id":"2508.16599","title":"Humans Perceive Wrong Narratives from AI Reasoning Texts","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2508.17291","title":"Meta-R1: Empowering Large Reasoning Models with Metacognition","created":"2025-08-24","cited_by_count":6,"area":"lr"},{"id":"2509.23676","title":"From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models","created":"2025-09-28","cited_by_count":6,"area":"lr"},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2512.18196","title":"LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision","created":"2025-12-20","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2603.17199","title":"Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2512.12777","title":"State over Tokens: Characterizing the Role of Reasoning Tokens","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2601.11517","title":"Do explanations generalize across large reasoning models?","created":"2026-01-16","cited_by_count":5,"area":"lr"},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"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":"2603.20172","title":"Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation","created":"2026-03-20","cited_by_count":4,"area":"lr"},{"id":"2603.26410","title":"Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models","created":"2026-03-27","cited_by_count":4,"area":"lr"},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2601.14553","title":"Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2605.24286","title":"Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning","created":"2026-05-22","cited_by_count":3,"area":"lr"},{"id":"2607.14345","title":"Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2605.24960","title":"Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization","created":"2026-05-24","cited_by_count":2,"area":"lr"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","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":"2509.17177","title":"FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions","created":"2025-09-21","cited_by_count":1,"area":"lr"},{"id":"2602.01017","title":"How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic Experiments","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2604.27251","title":"Compliance vs. Sensibility: On the Reasoning Controllability in Large Language Models","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2605.27901","title":"The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.23404","title":"ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2607.08173","title":"Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets","created":"2026-07-09","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":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","cited_by_count":1,"area":null},{"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":"2512.07288","title":"Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2604.15726","title":"LLM Reasoning Is Latent, Not the Chain of Thought","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.13290","title":"What properties of reasoning supervision are associated with improved downstream model quality?","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2606.11445","title":"Forecasting Future Behavior as a Learning Task","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.29481","title":"To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation","created":"2026-06-28","cited_by_count":0,"area":"lr"},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.04928","title":"Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?","created":"2026-08-05","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":"2609.06704","title":"Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models","created":"2026-09-06","cited_by_count":0,"area":"lr"},{"id":"2609.11360","title":"R4Tun: LLM-guided adaptive segmental tunnel lining segmentation in point clouds","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.15989","title":"Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.23065","title":"From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.25366","title":"From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2610.05472","title":"Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}