CoT Faithfulness

CoT: Chain-of-Thought

Ask about this topic

Overview

Chain-of-thought faithfulness studies whether a model actually uses its visible reasoning to reach an answer, rather than producing a plausible explanation after deciding. Researchers test this with counterfactual hints, edits or deletions of reasoning steps, causal activation patching, and probes of hidden states across settings such as math, medical question answering, and vision. Training approaches include rewards for causal dependence and sufficient evidence, preference learning, and structural constraints on shortcuts. A central challenge is that accuracy and plausible explanations do not establish faithfulness, while measurements vary by task and method and often transfer poorly across models or settings.

Latest papers

CardsList

73 papers4 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

  1. Correctness Conditioning as Selection in Chain-of-Thought Faithfulness Evaluation

    Oct 27, 2026Yueer Pan, Yuexi PanCoT FaithfulnessCausal Inference with Unobserved Confounding

    Zhejiang University · University of Science and Technology of China

  2. Verbalising Model's Computation for Chain-of-Thought Faithfulness Detection

    Oct 16, 2026Yujing Wang, Yulan He, Wenya Wang +1CoT FaithfulnessFaithfulness of Language Model Reasoning

    King’s College London · Nanyang Technological University

  3. The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls

    Oct 16, 2026Lucas Resck, Jingyi Sun, Qianli Wang +2CoT FaithfulnessFaithfulness of Language Model Reasoning

    Language Technology Lab, University of Cambridge · University of Copenhagen · Technische Universität Berlin +1

  4. SIFT: Robust Meta-Faithfulness Verification of Chain-of-Thought Reasoning Under Distribution Shift

    Oct 3, 2026Noor Islam S. Mohammad, Md. Basim Al Zabir Shammo, Hasan Siddiki +3CoT FaithfulnessLanguage Model Auditing

    Istanbul Technical University · Pabna University of Science and Technology · American International University-Bangladesh +2

  5. Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

    Sep 30, 2026Yihuai Hong, Shauli Ravfogel, Chen Zhao +1CoT FaithfulnessFaithfulness of Language Model Explanations

    New York University · NYU Shanghai

  6. Are Stated Reasoning Steps Causally Load-Bearing?

    Sep 22, 2026Abhiram Bhupatiraju, Rayan NyaupaneCoT FaithfulnessLLM Auditing

    The University of Texas at Austin

  7. From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought

    Sep 21, 2026Renee Jia, Di MuCoT FaithfulnessCausal Interventions in Language Models

    R2M AI, Cornell University · R2M AI, Carnegie Mellon University

  8. From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness

    Sep 19, 2026Qianli Wang, Yilong Wang, Dennis Wei +5CoT FaithfulnessLLM Interpretability

    Technische Universität Berlin · German Research Center for Artificial Intelligence (DFKI) · IBM Research +4

  9. Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition

    Sep 16, 2026Dohun Lee, Hyunwoo ParkCoT FaithfulnessLLM Auditing

    Graduate School of Data Science, Seoul National University

  10. Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation

    Sep 13, 2026Eduin E. Hernandez, Luis F. Garcia, Nurassyl Askar +2Multi-Hop QAKnowledge Graph Question Answering

    National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Independent Researcher

  11. CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making

    Sep 9, 2026Cagri TemelCoT FaithfulnessLarge Language Model-Based Robot Planning

    Hezarfen LLC Seattle, WA, USA · Grand Canyon University Phoenix, AZ, USA

  12. Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models

    Sep 6, 2026Bayar Menzat, Maximilian Süss, Ruizhi Wang +3CoT FaithfulnessFaithfulness in VLMs

    Vienna University of Technology, Austria · University of Oxford, UK · Imperial College London, UK +1

  13. Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning

    Sep 3, 2026Kevin Du, Alexander Hoyle, Laura Ruis +1CoT FaithfulnessProcess Reward Models

    ETH Zürich · Work done during an internship at Cohere. · MIT +1

  14. Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

    Aug 29, 2026Aryo Pradipta Gema, Neel Rajani, Rohit Saxena +2CoT FaithfulnessLLM Auditing

    University of Edinburgh · University of Edinburgh, Miniml.AI

  15. Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought

    Aug 25, 2026Mengzhu Xu, Jifan Gao, Xia Jiang +2CoT FaithfulnessCoT Evaluation

    Eindhoven University of Technology, Eindhoven, The Netherlands · Dana-Farber Cancer Institute, Boston, MA, USA

  16. FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation

    Aug 11, 2026Rob Cornish, Iacopo Ghinassi, Po-Hung Yeh +7CoT FaithfulnessLLM Sycophancy

    Nanyang Technological University, Singapore · University of Oxford, United Kingdom · The University of Edinburgh, United Kingdom

  17. SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification

    Aug 9, 2026Wenyao Cui, Huaping Zhang, Yongyi Huang +6CoT FaithfulnessLLM Answer Verification

    Beijing Institute of Technology Beijing, China · Zhongguancun Academy Beijing, China · Xinjiang Future Enterprise Incubator Co., Ltd. Xinjiang, China +1

  18. Risky Business: Measuring The Faithfulness-Safety Tension

    Aug 4, 2026Dominik Meier, Luca Joshua Francis, Marco Bernhard Kaiser +3CoT FaithfulnessLanguage Model Safety Evaluation

    University of Göttingen · 2Landeskriminalamt NRW

  19. Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression

    Aug 3, 2026Mengting Ai, Jingrui He, Yue GuoCoT FaithfulnessReasoning Evaluation

    University of Illinois Urbana-Champaign

  20. TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding

    Jul 31, 2026Sparsh Rastogi, Tanmay Kumar, Baiyu Chen +3CoT FaithfulnessHuman Activity Recognition

    University of New South Wales, Sydney, Australia · Thapar Institute of Engineering and Technology, Patiala, India

  21. On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness

    Jul 31, 2026Matthew Nguyen, Kyle Cox, Austin Meek +1CoT FaithfulnessLanguage Model Steering

    University of Virginia · Independent · University of Delaware +1

  22. A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models

    Jul 28, 2026Vivek Shukla, Varun Shukla, Atul +2CoT FaithfulnessMathematical Reasoning Benchmarks

    Allenhouse Institute of Technology Kanpur, India

  23. Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong

    Jul 26, 2026Suramya R. Angdembay, Dikshant Aryal, Nick RahimiCoT FaithfulnessCoT Evaluation

    The University of Southern Mississippi

  24. Not All LLM Reasoning is Visible in the Chain-of-Thought

    Jul 24, 2026Vatsal Baherwani, Tom Goldstein, Ashwinee PandaCoT FaithfulnessLLM Interpretability

    New York University · University of Maryland · TogetherAI

  25. Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad

    Jul 23, 2026Jiatong Li, Yuxuan Ren, Weida Wang +2CoT FaithfulnessChemical Reasoning in LLMs

    Blue Whale Lab, National University of Singapore · Fudan University · Hong Kong Polytechnic University

  26. CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness

    Jul 21, 2026Ziming Wang, Yinghua Yao, Changwu Huang +2CoT FaithfulnessFaithfulness of Language Model Explanations

    Department of Computer Science and Engineering of Southern University of Science and Technology, Shenzhen, China · Center for Frontier AI Research, Agency for Science, Technology and Research (A*STAR), Singapore · School of AI and Liberal Arts, Beijing Normal-Hong Kong Baptist University, Zhuhai, China +1

  27. Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evidence of Answer Pre-Commitment in an Open-Weight LLM

    Jul 17, 2026Heejin JoCoT FaithfulnessLLM Reasoning

  28. From Plausible to Actionable: A Position on LLM Self-Explanations

    Jul 17, 2026Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1CoT FaithfulnessFaithfulness of Language Model Explanations

    University of Utrecht, Utrecht, Netherlands · National Police Lab AI, Netherlands Police, Driebergen, Netherlands · Scuola Normale Superiore, Pisa, Italy +1

  29. Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution

    Jul 11, 2026Hironao NakamuraCoT FaithfulnessLLM Grounding

    Independent Researcher

  30. What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness

    Jul 9, 2026Raphaël Sarfati, Pratyush Ranjan Tiwari, Siddharth Boppana +3CoT FaithfulnessLanguage Model Calibration

    goodfire · eternis