most citedWhen Large Language Models are More PersuasiveThan Incentivized Humans, and Why

7 citations · 7 across the 5 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference

Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt

Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by assessing what it takes to m…