SOURCE-LINKED INTELLIGENCE

I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Vision-language models are increasingly used in settings where some input modalities may be unavailable, yet we know little about whether they can faithfully explain how such missing information affects their own predictions. We introduce an interventional protocol for evaluating self-explanations of modality dynamics: models state what each modality alone would support, whether restoring a missing modality would change their answer, and whether the available evidence is sufficient; we then execute the corresponding modality intervention and compare these claims with the model's realized behav

Read original source ↗ Open in workspace

recordType

paper

region

Global