Metraipolis › archive › dc_299076daed9c

Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation — arXiv:2608.07763

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07763
License (as archived)
CC0-1.0
Archived
2026-10-19T08:49:48.486Z
SHA-256 of the archived text
9db274948986b2381839dba9ccf702bdb0b02bc0f09bce82a50670a9385a8379
Stable URL of this page
https://metraipolis.com/documento/dc_299076daed9c

How to cite

Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation — arXiv:2608.07763 — arXiv (en), https://arxiv.org/abs/2608.07763 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_299076daed9c (Metraipolis archive dc_299076daed9c, sha256 9db274948986b2381839dba9ccf702bdb0b02bc0f09bce82a50670a9385a8379)
BibTeX
@misc{dc299076daed9c,
  title = {Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation — arXiv:2608.07763},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07763},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_299076daed9c; sha256 9db274948986b2381839dba9ccf702bdb0b02bc0f09bce82a50670a9385a8379},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07763. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) have achieved strong performance on tasks such as image captioning, visual question answering, and image-to-text generation. However, they are predominantly trained on English-centric data, which limits their ability to handle culturally grounded visual understanding and leads to failures in interpreting region-specific meanings, symbolic content, and context-dependent visual cues. Existing benchmarks for cultural competence are often template-driven and focused on surface-level recognition, making them insufficient for evaluating deeper linguistic and pragmatic understanding in culturally situated settings. We introduce PoVisLE, a monocultural vision-language benchmark for Polish designed to evaluate culturally grounded multimodal understanding under a grounded evaluation paradigm, where language is interpreted in interaction with visual context. The dataset contains 1,117 images and 2,366 manually annotated VQA pairs. Overall, our dataset provides a controlled and challenging resource for assessing culturally grounded vision-language understanding beyond surface-level recognition.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.07763 — 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 2026-10-19T08:49:41.832Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).