Paper Detail

MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages

Andrei-Alexandru Manea, Jindřich Libovický, Philipp J. Rösch

arxiv Score 17.8

Published 2026-11-02 · First seen 2026-11-03

General AI

Abstract

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 https://github.com/ufal/multi-inpaint-coco.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{manea2026multiinpaintcoco,
  title = {MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages},
  author = {Andrei-Alexandru Manea and Jindřich Libovický and Philipp J. Rösch},
  year = {2026},
  abstract = {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 fur},
  url = {https://arxiv.org/abs/2611.03309},
  keywords = {cs.CL},
  eprint = {2611.03309},
  archiveprefix = {arXiv},
}

Metadata

{}