Papers/2611.21644
🧪 Test?View on arXiv

MInfoVisQA: A Multilingual Benchmark for Information-Rich Visual Question Answering

multimodallanguage sensitivityvisual question answering
2611.21644
Builder Relevance
70%
15h ago

Abstract

This paper introduces MInfoVisQA, a benchmark to evaluate the performance of multimodal large language models on information-rich visuals across multiple languages.

Reality Card

Core Claim

The study reveals significant robustness gaps in MLLMs' performance on multilingual visual question answering tasks, highlighting the need for improved cross-language sensitivity metrics.

Method / Result

The evaluation of 25 MLLMs showed a mean LQA accuracy of 80.4%, with performance spreads of up to 20.3 percentage points across languages.

Limitations

The models consistently scored lower with non-English visuals under fixed English QA, indicating a limitation in cross-language adaptability.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers