Bridging the AI Language Divide: A Systematic Review of NMT and LLMs in Low-Resource Translation
Technologies · 21.08.2026 · 14 (8) · 518
DOI: 10.3390/technologies14080518 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Technologies, online erschienen am 21.08.2026. Verfasst von Sweeta Agrawal und 1 weiteren Autor:innen. Die Arbeit nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid evolution of AI-driven language technologies has inadvertently widened the gap between high-resource and marginalised languages. Despite significant progress in AI-driven translation for high-resource languages, low-resource languages remain underrepresented due to limited data, a lack of benchmarks, and evaluation challenges. This study presents a comprehensive systematic review of machine translation for low-resource languages, focusing on advances in neural machine translation (NMT) and large language models (LLMs) between 2017 and 2025. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 63 studies were selected from the 1696 articles in the Scopus, Web of Science, and Google Scholar databases. The review identifies five dominant methodological approaches: data augmentation, back-translation, transfer learning, pre-training, and parameter-efficient fine-tuning. The findings reveal that model performance is highly dependent on resource availability: transformer-based NMT excels in moderate data settings, while LLMs demonstrate promising zero-shot and few-shot capabilities in extremely low-resource scenarios. Hybrid NMT–LLM approaches emerge as a particularly effective paradigm. The study also highlights critical challenges, including the absence of standardised benchmarks, over-reliance on inadequate evaluation metrics such as Bilingual Evaluation Understudy (BLEU), limited human evaluation, and significant geographic and linguistic underrepresentation. Additionally, ethical concerns related to bias, cultural representation, and community engagement are increasingly relevant. The findings contribute to advancing inclusive and equitable AI-driven language technologies.
Zitieren
APA
Agrawal, S., & Agbeyangi, A. O. (2026). Bridging the AI Language Divide: A Systematic Review of NMT and LLMs in Low-Resource Translation. Technologies, 14(8), 518. https://doi.org/10.3390/technologies14080518
Vancouver
Agrawal S, Agbeyangi AO. Bridging the AI Language Divide: A Systematic Review of NMT and LLMs in Low-Resource Translation. Technologies. 2026;14(8):518. doi:10.3390/technologies14080518
BibTeX
@article{Agrawal2026,
author = {Agrawal, Sweeta and Agbeyangi, Abayomi O.},
title = {Bridging the AI Language Divide: A Systematic Review of NMT and LLMs in Low-Resource Translation},
journal = {Technologies},
year = {2026},
volume = {14},
number = {8},
pages = {518},
doi = {10.3390/technologies14080518}
}
EUVIMED