SOURCE-LINKED INTELLIGENCE

Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

We investigate how vision-language models (VLMs) handle context-memory conflicts; that is, situations in which the model is given information in context that differs from what was stored parametrically during training. We document asymmetric biases: models tend to prefer in-context information about entities which appear in text, but prefer parametric information about entities which appear in images. We relate this asymmetry to the late representational alignment across modalities, showing that the longer processing time associated with resolving visual entities prevents the suppression of th

Read original source ↗ Open in workspace

recordType

paper

region

Global