Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation
Read the original on arXiv AI →Persona prompting is widely used in LLM user simulation, yet it assumes that specifying a target user attribute will shift only that attribute while leaving others unchanged. Across multiple models, the study finds that changing a target attribute also alters unspecified non‑target choices, creating a "neutrality gap" that persists even when no preference is declared. The authors show that blocking query‑time attention reduces non‑target drift, but this also weakens target efficacy, highlighting a central challenge in achieving selective control.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.