EUVIMEDEUVIMED entdecken
Crossref

Multimodal large language models for low-resource languages and Global South deployment: A comprehensive survey of architectures, benchmarks, and sociotechnical challenges

Austin Olom Ogar, Abah Joshua, Aliyu Suleiman Muhammed, Oluwatobi Noah Akande, Faruk Obansa Muhammed, Ibrahim Anka Salihu

Science World Journal · 2026 · 21 (2) · 762-769

DOI: 10.4314/swj.v21i2.42 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science World Journal, 2026. Verfasst von Austin Olom Ogar und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal Large Language Models (MLLMs) such as LLaVA, InstructBLIP, and Qwen2-VL have unlocked joint reasoning over text and images at an unprecedented scale. The technical literature on MLLM efficiency, domain adaptation, and benchmarking has matured into a substantial corpus. However, the overwhelming majority of surveys are written from the vantage point of high-resource English-language datasets and well-resourced computing infrastructures. This survey takes a different angle. We consolidate the recent literature on multimodal language understanding through the lens of low-resource languages and Global South deployment contexts, where data scarcity, compute constraints, intermittent connectivity, and sociotechnical-trust considerations interact in ways that high-resource surveys rarely address. We propose a four-quadrant taxonomy that organises the field around linguistic coverage, data scarcity, compute constraints, and sociotechnical trust. We trace the evolution of multilingual multimodal architectures across an eight-year arc, map the benchmark landscape against nine languages and five modalities, and describe a three-tier edge-regional-global deployment topology suited to low-resource environments. Five high-impact application domains are surveyed: healthcare, agriculture, education, disaster response, and public service. A dedicated section examines sociotechnical considerations, including linguistic justice, algorithmic fairness, and regulatory readiness. We identify six concrete open research problems and outline a future research agenda. The survey is intended as a single-source reference for researchers, policy makers, and practitioners pursuing equitable multimodal AI deployment in low-resource contexts.

Zitieren

APA

Ogar, A. O., Joshua, A., Muhammed, A. S., Akande, O. N., Muhammed, F. O., & Salihu, I. A. (2026). Multimodal large language models for low-resource languages and Global South deployment: A comprehensive survey of architectures, benchmarks, and sociotechnical challenges. Science World Journal, 21(2), 762-769. https://doi.org/10.4314/swj.v21i2.42

Vancouver

Ogar AO, Joshua A, Muhammed AS, Akande ON, Muhammed FO, Salihu IA. Multimodal large language models for low-resource languages and Global South deployment: A comprehensive survey of architectures, benchmarks, and sociotechnical challenges. Science World Journal. 2026;21(2):762-769. doi:10.4314/swj.v21i2.42

BibTeX
@article{Ogar2026,
  author = {Ogar, Austin Olom and Joshua, Abah and Muhammed, Aliyu Suleiman and Akande, Oluwatobi Noah and Muhammed, Faruk Obansa and Salihu, Ibrahim Anka},
  title = {Multimodal large language models for low-resource languages and Global South deployment: A comprehensive survey of architectures, benchmarks, and sociotechnical challenges},
  journal = {Science World Journal},
  year = {2026},
  volume = {21},
  number = {2},
  pages = {762--769},
  doi = {10.4314/swj.v21i2.42}
}
Kostenlos starten →