It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty

ArXi:2605.27288v1 Announce Type: cross Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behavior to sycophancy learned during reinforcement learning from human feedback, we hypothesize that conformity is also driven by a model's epistemic uncertainty at inference time. In this paper, we