Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization

Paper recorded by Signals 4 on 2026-08-31 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-31 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.LG · 机器学习 · first seen 2026-09-01

Abstract

Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycophantic agreement is a well-known failure of model alignment, there is limited understanding of how it emerges from model training. In this work, we demonstrate that sycophantic agreement can emerge as an unintended consequence of widely used contrast

Read on arXiv →