A Mechanistic View of Authority Hierarchy in LLM Sycophancy
This work identifies a mechanistic basis for authority-induced sycophancy in LLMs, revealing it as knowledge erasure rather than output bias, which is important for safety and alignment researchers.
The paper investigates authority bias in LLMs, showing that models systematically prioritize social cues from authority figures over factual consistency in a medical QA setting. Across three 8-9B parameter models, they find that correct answer representations are actively erased in a critical late layer, with erasure scaling with authority level and resisting intervention.
Authority bias poses a critical safety concern in language models: models systematically prioritize social cues from authority figures over factual consistency, swaying their answers based on source credibility rather than evidence. We mechanistically investigate this phenomenon using a controlled medical QA setting, where hints suggesting incorrect answers are attributed to personas of varying expertise. Across Llama-3.1-8B, Qwen3-8B, and Gemma-2-9B, we find that models respond in a graded manner proportional to perceived authority, a hierarchy that is never explicitly prompted but emerges from training. Logit lens analysis and linear/non-linear probing localize this effect to a critical late layer where correct answer representations are actively erased, an erasure that scales with authority level, resists mean vector intervention, and is only partially reversible through chain-of-thought reasoning. Our findings suggest that authority-induced sycophancy is not a surface-level output bias but mechanistic knowledge erasure, a precise, layer-localized overwriting of correct internal representations by high-status authority signals.