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

arxiv.org · 749 words · saved by 1 readers

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

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

related reading