Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy
This story is from 2026-09-02. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.00067v1 Announce Type: new Abstract: 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 extern…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-02 04:00 · arXiv cs.CL
Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy