[2405.18915] Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasoners

Large language models (LLMs) suffer from serious unfaithful chain-of-thought (CoT) issues. Previous work attempts to measure and explain it but lacks in-depth analysis within CoTs and does not consider the interactions…

Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasoners Jiachun Li 1,2 , Pengfei Cao 1,2 , Yubo Chen 1,2 , Kang Liu 1,2 , Jun Zhao 1,2 1 School of Artificial Intelligence, University of Chinese Academy of Sciences 2 The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences {jiachun.li, pengfei.cao, yubo.chen, kliu, jzhao} @nlpr.ia.ac.cn Abstract Large language models (LLMs) suffer from serious unfaithful chain-of-thought (CoT) issues. Previous work attempts to measure and explain it but lacks in-depth

related reading

• Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasonersarxiv.org
• [2412.06769] Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• the case for CoT unfaithfulness is overstated — LessWronglesswrong.com
• Measuring Faithfulness in Chain-of-Thought Reasoning \ Anthropicanthropic.com
• Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignmentarxiv.org
• [2510.24941] Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thoughtarxiv.org
• [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org
• [2510.09714] All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Languagearxiv.org
• Faithful Reasoning (with LLMs)arxiv.org