AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

DiaVLo: Diagnosing Behaviours of Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Vision-language models (VLMs) rely on storing and transferring appropriate information across their sub-components. Verifying that the VLMs exhibit desired behaviours, while avoiding harmful ones, is central to their reliable deployment. Yet, methods that identify VLM behaviours remain scarce. We present DiaVLo, a diagnostic framework that leverages human curation and VLMs' generation capabilities to construct specifications of desired and observed VLM behaviours, surfacing potential misalignments. Beyond this, DiaVLo also provides causal estimates to identify the most influential concepts ste

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-23T13:51:27.104Z. This is not the publication date.