SOURCE-LINKED INTELLIGENCE

Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

External text can override conflicting image evidence in multimodal large language models, a failure we call multimodal contextual sycophancy. We introduce a 998-case diagnostic that independently varies visual evidence, commonsense priors, and external text, and probe when this failure arises by moving the information boundary around a context-blind visual witness. On abnormal images paired with Gemini-generated false text, GPT-5.1 scores 7.9% under joint conditioning, 49.7% when the context-blind witness report is scored directly, 63.7% under a matched two-call witness-arbiter pipeline that

Read original source ↗ Open in workspace

recordType

paper

region

Global