Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs
It addresses the critical challenge of enhancing multilingual capabilities in LLMs without extensive fine-tuning, which is incremental as it builds on existing methods like RAG.
The paper tackles the problem of improving multilingual performance in LLMs for non-Latin scripts and low-resource languages, achieving 10-15% improvements over pre-trained models and 4x gains compared to fine-tuned models.
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 across 18 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.