Shiromani, S., Chaudhury, A., & Kunda, S. P. (2026). The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders.
Chicago Style (17th ed.) CitationShiromani, Shikhar, Archie Chaudhury, and Sri Pranav Kunda. The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders. 2026.
MLA (9th ed.) CitationShiromani, Shikhar, et al. The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders. 2026.
Advarsel: Disse citationer er muligvist ikke 100% nøjagtige.