Metraipolis › archive › dc_49daecb998b9
MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages — arXiv:2611.03309
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03309
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:23:51.528Z
- SHA-256 of the archived text
b45c0ff7417361d4312eb485cb2758058a23172ce0267dd0d735f74802b6fa84- Stable URL of this page
https://metraipolis.com/documento/dc_49daecb998b9
How to cite
MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages — arXiv:2611.03309 — arXiv (en), https://arxiv.org/abs/2611.03309 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49daecb998b9 (Metraipolis archive dc_49daecb998b9, sha256 b45c0ff7417361d4312eb485cb2758058a23172ce0267dd0d735f74802b6fa84)
BibTeX
@misc{dc49daecb998b9,
title = {MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages — arXiv:2611.03309},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03309},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49daecb998b9; sha256 b45c0ff7417361d4312eb485cb2758058a23172ce0267dd0d735f74802b6fa84},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03309. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Previous research shows that vision-language (VL) models struggle to understand fine-grained image details and tend to focus on the overall layout. Moreover, any weakness in English tends to be further amplified in the multilingual setting. To study that, we extend InpaintCOCO, an English dataset focused on fine-grained visual details, to 13 typologically diverse languages across five language families, creating MultiInpaintCOCO - a new multilingual benchmark of 953 minimal-pair examples. We further test several state-of-the-art models in multilingual multimodal retrieval, considering both light VL CLIP-like encoders and large language models. Our results show that performance degrades substantially for lower-resource languages, with the strongest predictor being the data resources available for the languages rather than typological similarity to English. In cross-lingual retrieval, most models exhibit a systematic bias toward English: when given a correct caption in a non-English language and an incorrect one in English, models preferentially select the English caption. This bias varies considerably across architectures. Among the tested models, Gemma 3 shows the strongest English preference while Qwen 3 is the least biased, despite both reaching similar monolingual accuracy across languages. The code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.03309 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:10:07.994Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).