Dissociating the Internal Representations of Sycophancy in LLMs

Excerpt

arXiv:2607.07003v3 Announce Type: replace Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, agreeing with a user's statement even when it is incorrect. While often studied as a single, uniform behavior, sycophancy can manifest in substantially distinct ways across contexts, raising the question of whether this heterogeneity is reflected in its internal mechanisms. To address this gap, we dissociate the representations of sycophancy into factual and opinion subtypes, motivated