SCIENCE@home

Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains

Yurii Paniv,Artur Kiulian,Dmytro Chaplynskyi,M. Khandoga,Anton Polishko,Tetiana Bas,Guillermo Gabrielli

Published 2024 in Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025)

ABSTRACT

While the evaluation of multimodal English-centric models is an active area of research with numerous benchmarks, there is a profound lack of benchmarks or evaluation suites for low- and mid-resource languages. We introduce ZNO-Vision, a comprehensive multimodal Ukrainian-centric benchmark derived from standardized university entrance examination (ZNO). The benchmark consists of over 4,300 expert-crafted questions spanning 12 academic disciplines, including mathematics, physics, chemistry, and humanities. We evaluated the performance of both open-source models and API providers, finding that only a handful of models performed above baseline. Alongside the new benchmark, we performed the first evaluation study of multimodal text generation for the Ukrainian language: we measured caption generation quality on the Multi30K-UK dataset, translated the VQA benchmark into Ukrainian, and measured performance degradation relative to original English versions. Lastly, we tested a few models from a cultural perspective on knowledge of national cuisine. We believe our work will advance multimodal generation capabilities for the Ukrainian language and our approach could be useful for other low-resource languages.

PUBLICATION RECORD

  • Publication year

    2024

  • Venue

    Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025)

  • Publication date

    2024-11-22

  • Fields of study

    Physics, Chemistry, Computer Science, Linguistics, Education

  • Identifiers
    DOI 10.48550/arXiv.2411.14647arXiv 2411.14647
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-23 of 23 references · Page 1 of 1

CITED BY