[2305.04388] Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2305.04388] Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2305.04388 (cs) [Submitted on 7 May 2023 ( v1 ), last revised 9 Dec 2023 (this version, v2)] Title: Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting Authors: Miles Turpin , Julian Michael , Ethan Perez , Samuel R. Bowman View a PDF of

related reading

• the case for CoT unfaithfulness is overstated — LessWronglesswrong.com
• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• [2405.18915] Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasonersar5iv.labs.arxiv.org
• Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasonersarxiv.org
• Measuring Faithfulness in Chain-of-Thought Reasoning \ Anthropicanthropic.com
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Reasoning models don't always say what they think \ Anthropicanthropic.com
• Externalized reasoning oversight: a research direction for language model alignment — AI Alignment Forumalignmentforum.org
• [2510.24941] Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thoughtarxiv.org
• Thought Branches: Interpreting LLM Reasoning Requires Resamplingarxiv.org
• [2505.05410] Reasoning Models Don't Always Say What They Thinkarxiv.org
• When Chain of Thought is Necessary, Language Models Struggle to Evade Monitorsarxiv.org