Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs

Somnath Kumar, Vaibhav Balloli, Mercy Ranjit, Kabir Ahuja, Sunayana Sitaram, Kalika Bali, Tanuja Ganu, Akshay Nambi


Abstract
Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive fine-tuning. We introduce a novel dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime. By adapting configurations dynamically, our method achieves significant improvements over static, best and random baselines. It operates efficiently in both offline and online settings, generalizing seamlessly across new languages and datasets. Leveraging Retrieval-Augmented Generation (RAG) with state-of-the-art multilingual embeddings, we achieve superior task performance across diverse linguistic contexts. Through systematic investigation and evaluation across18 diverse languages using popular question-answering (QA) datasets we show our approach results in 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models.
Anthology ID:
2025.coling-main.619
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9209–9223
Language:
URL:
https://aclanthology.org/2025.coling-main.619/
DOI:
Bibkey:
Cite (ACL):
Somnath Kumar, Vaibhav Balloli, Mercy Ranjit, Kabir Ahuja, Sunayana Sitaram, Kalika Bali, Tanuja Ganu, and Akshay Nambi. 2025. Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9209–9223, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs (Kumar et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.619.pdf