Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation

Researchers introduced PuMVR, a benchmark of 1,000 image-text pairs across Punjabi's three scripts, and found that state-of-the-art vision-language models show a systematic Script Gap, with accuracy differences up to 16% and script consistency rates as low as 24.8%. The findings reveal that current multilingual VLMs are not truly multi-script, highlighting the need for script-agnostic evaluation to ensure equitable AI access.

arXiv:2606.17188v1 Announce Type: new Abstract: Current multilingual evaluations for Vision-Language Models VLMs assume a one-to-one mapping between language and orthography, overlooking billions of users of multi-script languages. We introduce PuMVR Punjabi Multimodal Visual Reasoning , a benchmark of 1,000 strictly parallel image-text instances across Punjabi's three active scripts: Gurmukhi, Shahmukhi, and Roman. Evaluating 10 state-of-the-art VLMs, we expose a substantial and systematic Script Gap. Models frequently solve visual tasks in one script while failing identical tasks in another, with accuracy deltas reaching 16%. Crucially, visual input boosts absolute performance uniformly yet does not close the orthographic gap. Furthermore, cross-script in-context transfer is highly brittle, exposing script-locked knowledge representation. Supported by McNemar tests across all script pairs, our findings demonstrate that current "multilingual" VLMs are not truly multi-script. We propose the Script Consistency Rate SCR , which falls as low as 24.8% on our benchmark, as a mandatory metric for script-agnostic evaluation to ensure equitable AI access. Data and code are available at: https://github.com/prabhjotschugh/Not-Truly-Multilingual-PuMVR.