SOURCE-LINKED INTELLIGENCE

Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?

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

Recent multilingual vision--language encoders cover hundreds of languages in a single model, yet on two state-of-the-art instances retrieval on low-resource languages (LRL; e.g. Swahili) trails high-resource ones (HRL; e.g. English) by $30^+$\,pp. We ask where in the trained encoder this gap is located. Prior modality-gap and cross-lingual subspace work suggests a linear language direction at the output crowds out alignment-relevant geometry. We falsify this: LEACE drives the linear language classifier from $>99\%$ to near chance and iterated INLP to $37$--$50\%$ while LRL retrieval moves with

Read original source ↗ Open in workspace

recordType

paper

region

Global