Cross-Lingual Summarization for Low-Resource Languages Using Multilingual Retrieval-Based In-Context Learning
Applied Sciences · 11.07.2025 · 15 (14) · 7800
DOI: 10.3390/app15147800 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 11.07.2025. Verfasst von Gyutae Park und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT), Chung-Ang University Graduate Research Scholarship in 2023.
Abstract (Originalsprache)
Cross-lingual summarization (XLS) involves generating a summary in one language from an article written in another language. XLS presents substantial hurdles due to the complex linguistic structures across languages and the challenges in transferring knowledge effectively between them. Although Large Language Models (LLMs) have demonstrated capabilities in cross-lingual tasks, the integration of retrieval-based in-context learning remains largely unexplored, despite its potential to overcome these linguistic barriers by providing relevant examples. In this paper, we introduce Multilingual Retrieval-based Cross-lingual Summarization (MuRXLS), a robust framework that dynamically selects the most relevant summarization examples for each article using multilingual retrieval. Our method leverages multilingual embedding models to identify contextually appropriate demonstrations for various LLMs. Experiments across twelve XLS setups (six language pairs in both directions) reveal a notable directional asymmetry: our approach significantly outperforms baselines in many-to-one (X→English) scenarios, while showing comparable performance in one-to-many (English→X) directions. We also observe a strong correlation between article-example semantic similarity and summarization quality, demonstrating that intelligently selecting contextually relevant examples substantially improves XLS performance by providing LLMs with more informative demonstrations.
Förderung
- Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT)
- Chung-Ang University Graduate Research Scholarship in 2023
Zitieren
APA
Park, G., Park, J., & Lee, H. (2025). Cross-Lingual Summarization for Low-Resource Languages Using Multilingual Retrieval-Based In-Context Learning. Applied Sciences, 15(14), 7800. https://doi.org/10.3390/app15147800
Vancouver
Park G, Park J, Lee H. Cross-Lingual Summarization for Low-Resource Languages Using Multilingual Retrieval-Based In-Context Learning. Applied Sciences. 2025;15(14):7800. doi:10.3390/app15147800
BibTeX
@article{Park2025,
author = {Park, Gyutae and Park, Jeonghyun and Lee, Hwanhee},
title = {Cross-Lingual Summarization for Low-Resource Languages Using Multilingual Retrieval-Based In-Context Learning},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {14},
pages = {7800},
doi = {10.3390/app15147800}
}
EUVIMED