arXiv · 2611.21644
MInfoVisQA: A Multilingual Benchmark for Information-Rich Visual Question Answering
Abstract
Multimodal large language models (MLLMs) excel in vision-language tasks; yet, whether they maintain consistent understanding of information-rich visuals (InfoVis) when the surface language changes remains unclear. To quantify this capability, we introduce MInfoVisQA, a parallel benchmark with 8,960 QA configurations derived from 128 seed instances across 24 languages. We construct seed-matched, language-parallel visuals and QA pairs by disentangling numerical-structural data from text and programmatically synchronizing translated labels. We evaluate 25 MLLMs under two settings: Language-Aligned QA (LQA, matching visual-text languages) and Cross-Language QA (XQA, fixed QA language with varying visual languages). The results show that aggregate accuracy masks substantial robustness gaps: two models with comparable mean LQA accuracy (80.4\%) exhibit performance spreads of 7.8 and 20.3 percentage points across languages. Moreover, all 25 models score lower with non-English visuals under fixed English QA, underscoring the need for cross-language sensitivity metrics.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Changjiang Jiang, Jiang Zhou, Xinbin Yuan, Fan Zhang, Tao Feng, Zhuohan Xie. 2026-10-14. MInfoVisQA: A Multilingual Benchmark for Information-Rich Visual Question Answering. https://searcharxiv.com/abs/2611.21644
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.