CoT Faithfulness

CoT: Chain-of-Thought

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 54

All topics

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment
Sep 30, 2026Yihuai Hong, Shauli Ravfogel, Chen Zhao +1CoT Faithfulness Faithfulness of Language Model Explanations
New York University · NYU Shanghai
From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought
Sep 21, 2026Renee Jia, Di MuCoT Faithfulness Causal Interventions in Language Models
R2M AI, Cornell University · R2M AI, Carnegie Mellon University
From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
Sep 19, 2026Qianli Wang, Yilong Wang, Dennis Wei +5CoT Faithfulness LLM Interpretability
Technische Universität Berlin · German Research Center for Artificial Intelligence (DFKI) · IBM Research +4
Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition
Sep 16, 2026Dohun Lee, Hyunwoo ParkCoT Faithfulness LLM Auditing
Graduate School of Data Science, Seoul National University
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 Faithfulness Large Language Model-Based Robot Planning
Hezarfen LLC Seattle, WA, USA · Grand Canyon University Phoenix, AZ, USA
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning
Sep 3, 2026Kevin Du, Alexander Hoyle, Laura Ruis +1CoT Faithfulness Process Reward Models
ETH Zürich · Work done during an internship at Cohere. · MIT +1
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 Faithfulness LLM Auditing
University of Edinburgh · University of Edinburgh, Miniml.AI
FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation
Aug 11, 2026Rob Cornish, Iacopo Ghinassi, Po-Hung Yeh +7CoT Faithfulness LLM Sycophancy
Nanyang Technological University, Singapore · University of Oxford, United Kingdom · The University of Edinburgh, United Kingdom
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
Aug 9, 2026Wenyao Cui, Huaping Zhang, Yongyi Huang +6CoT Faithfulness LLM Answer Verification
Beijing Institute of Technology Beijing, China · Zhongguancun Academy Beijing, China · Xinjiang Future Enterprise Incubator Co., Ltd. Xinjiang, China +1
Risky Business: Measuring The Faithfulness-Safety Tension
Aug 4, 2026Dominik Meier, Luca Joshua Francis, Marco Bernhard Kaiser +3CoT Faithfulness Language Model Safety Evaluation
University of Göttingen · 2Landeskriminalamt NRW
Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression
Aug 3, 2026Mengting Ai, Jingrui He, Yue GuoCoT Faithfulness Reasoning Evaluation
University of Illinois Urbana-Champaign
TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding
Jul 31, 2026Sparsh Rastogi, Tanmay Kumar, Baiyu Chen +3CoT Faithfulness Human Activity Recognition
University of New South Wales, Sydney, Australia · Thapar Institute of Engineering and Technology, Patiala, India
On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
Jul 31, 2026Matthew Nguyen, Kyle Cox, Austin Meek +1CoT Faithfulness Language Model Steering
University of Virginia · Independent · University of Delaware +1
A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models
Jul 28, 2026Vivek Shukla, Varun Shukla, Atul +2CoT Faithfulness Mathematical Reasoning Benchmarks
Allenhouse Institute of Technology Kanpur, India
Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong
Jul 26, 2026Suramya R. Angdembay, Dikshant Aryal, Nick RahimiCoT Faithfulness CoT Evaluation
The University of Southern Mississippi
Not All LLM Reasoning is Visible in the Chain-of-Thought
Jul 24, 2026Vatsal Baherwani, Tom Goldstein, Ashwinee PandaCoT Faithfulness LLM Interpretability
New York University · University of Maryland · TogetherAI
Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad
Jul 23, 2026Jiatong Li, Yuxuan Ren, Weida Wang +2CoT Faithfulness Scientific Reasoning
Blue Whale Lab, National University of Singapore · Fudan University · Hong Kong Polytechnic University
CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness
Jul 21, 2026Ziming Wang, Yinghua Yao, Changwu Huang +2CoT Faithfulness Faithfulness 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
Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evidence of Answer Pre-Commitment in an Open-Weight LLM
Jul 17, 2026Heejin JoCoT Faithfulness LLM Reasoning
From Plausible to Actionable: A Position on LLM Self-Explanations
Jul 17, 2026Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1CoT Faithfulness Faithfulness of Language Model Explanations
University of Utrecht, Utrecht, Netherlands · National Police Lab AI, Netherlands Police, Driebergen, Netherlands · Scuola Normale Superiore, Pisa, Italy +1
Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution
Jul 11, 2026Hironao NakamuraCoT Faithfulness LLM Grounding
Independent Researcher
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 Faithfulness Language Model Calibration
goodfire · eternis
Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework
Jul 9, 2026Riccardo Revalor, Jalees Rehman, Debjit PalCoT Faithfulness LLM Reasoning with Graphs
¶Department of Electrical and Computer Engineering · ‡Department of Biochemistry and Molecular Genetics
Length Penalties Make Chain-of-Thought Less Monitorable
Jul 8, 2026Bryce LittleCoT Faithfulness Overthinking in Language Models
Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories
Jul 7, 2026Hengyu Jin, Shu Yang, Di WangCoT Faithfulness Continuous Latent Reasoning
Tongji University · Provable Responsible AI and Data Analytics (PRADA) Lab · King Abdullah University of Science and Technology
Detecting Answer-Driven Reasoning in LLM-Based Educational Tutors via Truncated Chain-of-Thought Auditing
Jul 6, 2026Bonan Shen, Dingyan Shang, Youting Wang +1CoT Faithfulness Intelligent Tutoring Systems
Independent Researcher United States · Northeastern University Boston, MA, USA · Syracuse University Syracuse, NY, USA
Do Models Read What They Write? Causal Registers in Scratchpad Reasoning
Jun 28, 2026Benjamin Shih, John Winnicki, Eric DarveCoT Faithfulness CoT Reasoning
Institute for Computational and Mathematical Engineering Stanford University
To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation
Jun 28, 2026Jiuheng Lin, Chen Zhang, Yansong FengCoT Faithfulness Reward Modeling
Wangxuan Institute of Computer Technology, Peking University
GRACE: Step-Level Benchmark for Faithful Reasoning over Context
Jun 15, 2026Hoang Pham, Dong Le, Anh Tuan LuuCoT Faithfulness Contextual Faithfulness
Nanyang Technological University · VinUniversity
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
Jun 11, 2026Daniel Scalena, Sara Candussio, Luca Bortolussi +3CoT Faithfulness LLM Interpretability
CLCG, University of Groningen · University of Milano-Bicocca · University of Trieste +1

Sep 30, 2026, cs.CLJ/K move · Enter open · S save

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

Yihuai Hong, Shauli Ravfogel, Chen Zhao, Eunsol Choi

New York University · NYU Shanghai

CoT Faithfulness Faithfulness of Language Model Explanations LLM Auditing LLM Interpretability

Open paper AskPDF arXiv

Chain-of-thought (CoT) traces often serve as a proxy for how Large Language Models (LLMs) arrive at their answers. However, growing evidence shows that models' CoT often fails to reflect their internal computations and can be changed without affecting their final answers. In this work, we measure and improve the alignment between the reasoning described in an LLM's CoT and what it computes internally. We propose CoT-Interpretability Alignment (CIA), a metric that measures the agreement between a model's CoT traces and its internal reasoning strategies as detected by interpretability tools. We evaluate CIA on three tasks (two-hop question answering, hint intervention, and integer multiplication) across three LLMs, finding that LLMs exhibit limited alignment across all tasks (44.8-75.9%). We then experiment with improving CIA via post-training, setting both the task accuracy and parametric faithfulness signals as a reward. Experiments show that we can substantially improve CoT parametric faithfulness while maintaining or improving the task accuracy. We provide rich analysis, such as their generalization patterns. Our work provides both a framework for auditing CoT parametric faithfulness and a pathway toward making models' explicit reasoning more trustworthy. Code and data are available at https://github.com/yihuaihong/CIA-minimal-repro.

Momentum

Related topics

Latest papers 54