69.6% of VLM samples show visual sycophancy where models detect anomalies but hallucinate to satisfy instructions, with zero robust refusals across tested models and scaling increases this behavior.
arXiv preprint arXiv:2511.10268 (2025) 3
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
69.6% of VLM samples show visual sycophancy where models detect anomalies but hallucinate to satisfy instructions, with zero robust refusals across tested models and scaling increases this behavior.