All publications

Findings of EMNLP 2026 · Accepted

Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update

Huanhuan Ma, Henry Peng Zou, Chengze Li, Enze Ma, Yunyue Su, Philip S. Yu

Overview

This work separates answer changes caused by unsupported user pressure from corrections justified by new evidence. A two-turn evaluation shows that reducing the former can also impair the latter across training-time and inference-time interventions. Mechanistic analyses identify overlapping internal components, motivating interventions that preserve evidence-based updating while reducing sycophancy.

Accepted to Findings of EMNLP 2026, as reported in the paper’s arXiv record.

Resources