EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Applying Multimodal Large Language Models for Visual Question Answering: Toward Vietnamese Educational Reasoning Systems

Xinh Le, Tho Quan, Tien-Thinh Nguyen

International Journal of Innovative Computing · 10.06.2026 · 16 (1) · 109-114

DOI: 10.11113/ijic.v16n1.680 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Computing, online erschienen am 10.06.2026. Verfasst von Xinh Le und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual Question Answering (VQA) is rapidly advancing due to Multimodal Large Language Models (MLLMs), which demonstrate powerful complex reasoning capabilities. However, this progress is predominantly centered on English and general-domain contexts. Domain-specific fields, such as STEM education, and low-resource languages, such as Vietnamese, remain significantly underserved, lacking both standardized datasets and specialized reasoning models. This research addresses this gap by investigating how MLLMs can be adapted for Vietnamese educational settings. As a foundational step, the ViPPS dataset (Vietnamese Physics Problem Solving) has been constructed and publicly released, the first multimodal dataset for physics problem solving in Vietnamese. Initial experiments on ViPPS show that current MLLMs achieve promising results, but still struggle with domain-specific reasoning and numerical accuracy. Based on these observations, the next stage of this research will focus on expanding the ViPPS dataset in both scale and scope, developing and evaluating advanced text-image reasoning and calculation mechanisms and extending these capabilities to VideoQA and model explainability. This research will contribute critical resources and methods, advancing the field of educational VQA for low-resource languages.

Zitieren

APA

Le, X., Quan, T., & Nguyen, T. (2026). Applying Multimodal Large Language Models for Visual Question Answering: Toward Vietnamese Educational Reasoning Systems. International Journal of Innovative Computing, 16(1), 109-114. https://doi.org/10.11113/ijic.v16n1.680

Vancouver

Le X, Quan T, Nguyen T. Applying Multimodal Large Language Models for Visual Question Answering: Toward Vietnamese Educational Reasoning Systems. International Journal of Innovative Computing. 2026;16(1):109-114. doi:10.11113/ijic.v16n1.680

BibTeX
@article{Le2026,
  author = {Le, Xinh and Quan, Tho and Nguyen, Tien-Thinh},
  title = {Applying Multimodal Large Language Models for Visual Question Answering: Toward Vietnamese Educational Reasoning Systems},
  journal = {International Journal of Innovative Computing},
  year = {2026},
  volume = {16},
  number = {1},
  pages = {109--114},
  doi = {10.11113/ijic.v16n1.680}
}
Kostenlos starten →