Shu-Yi Fan

Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit

LLM-judge audits assess bias by comparing ratings across matched conditions. Difference-in-differences designs compare two candidate responses within each item and then compare that contrast across a manipulated attribute. We show in closed form that this endpoint need not identify differential preference on the latent...