Analysis of three hypothesized modes of sycophancy shows that sycophancy is not a monolithic tendency, but a structured family of representationally and computationally distinct modes, motivating more precise measurement and intervention.
Abstract
Large language models often align with users'beliefs at the expense of factual accuracy, a behavior known as sycophancy. Prior mechanistic studies largely treat sycophancy as a single behavioral dimension that can be uniformly amplified or suppressed. We challenge this assumption by analyzing three hypothesized modes of sycophancy across 948 social pressure situations. Although the modes produce highly similar outputs, with a text-only classifier achieving just 57.8 percent accuracy, their internal representations are perfectly linearly separable from layer 14 onward. We further find the modes emerge at different processing stages, rely on distinct attention circuitry, and fire strongest on different inputs. These results show that sycophancy is not a monolithic tendency, but a structured family of representationally and computationally distinct modes, motivating more precise measurement and intervention.
This thesis presents a unified comparative analysis evaluating the robustness of three open-weights instruction-tuned models against a series of adversarial probing strategies spanning social, conversational, and analytical pressure, revealing that modern alignment strategies such as Reinforcement Learning from Human F...
Antia Alonso Cancela, Tom Kouwenhoven, Michiel van der Meer· 0 citations
A central concern with language models is sycophancy: their tendency to defer to users'views at the expense of independent substantive judgment. In parallel, work on social sycophancy has focused on behaviors such as validation and positivity that may signal inappropriate deference. Yet the markers of social sycophancy...
C. Isley, Johann D. Gaebler, Max Lamparth et al.· 0 citations
Large language models are increasingly asked to analyze data and report what the results mean, a task distinct from the belief- or preference-alignment settings studied in most sycophancy research. We test whether editorial framing in the prompt, ranging from a neutral request to an explicit instruction to search exhau...
Large language models often exhibit sycophancy, revising their answers to align with users when users push back. Such answer flips, however, can arise from different causes. One possibility is that the model simply aligns with the user's feedback in order to satisfy them. Another is that the feedback genuinely contains...
Huanhuan Ma, Henry Peng Zou, Cheng-Ze Li et al.· 0 citations
A framework that disentangles two distinct triggers of political sycophancy: opinion (aligning with explicit narratives) and identity (stereotyping based on demographic labels) is introduced, highlighting how personalization may amplify identity- or opinion-conditioned shifts in the model's behaviors.
Li-Ni Fu, Chang-Chih Meng, Chien-Hua Chen et al.· 0 citations
Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses ac...
Katherine Van Koevering, Anjalie Field· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
