Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs

ArXi:2509.21305v3 Announce Type: replace Large language models (LLMs) often exhibit sycophantic behaviors -- such as excessive agreement with or flattery of the user -- but it is unclear whether these behaviors arise from a single mechanism or multiple distinct processes. We decompose sycophancy into sycophantic agreement and sycophantic praise, contrasting both with genuine agreement.