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

TL;DR

This paper introduces innovative prompt optimization, hybrid retrieval-augmented generation, and dynamic adaptation techniques to significantly enhance multilingual performance of large language models without extensive retraining.

Contribution

It presents a novel dynamic learning framework that optimizes multilingual LLM performance through prompt tuning, hybrid methods, and real-time strategy selection, outperforming static approaches.

Findings

Performance improvements across multiple languages using prompt optimization

Enhanced multilingual task accuracy with hybrid retrieval-augmented generation

Dynamic adaptation outperforms static and random strategies in multilingual settings

Abstract

Large language models (LLMs) are at the forefront of transforming numerous domains globally. However, their inclusivity and effectiveness remain limited for non-Latin scripts and low-resource languages. This paper tackles the imperative challenge of enhancing the multilingual performance of LLMs without extensive training or fine-tuning. Through systematic investigation and evaluation of diverse languages using popular question-answering (QA) datasets, we present novel techniques that unlock the true potential of LLMs in a polyglot landscape. Our approach encompasses three key strategies that yield significant improvements in multilingual proficiency. First, by meticulously optimizing prompts tailored for polyglot LLMs, we unlock their latent capabilities, resulting in substantial performance boosts across languages. Second, we introduce a new hybrid approach that synergizes LLM Retrieval Augmented Generation (RAG) with multilingual embeddings and achieves improved multilingual task performance. Finally, we introduce a novel learning approach that dynamically selects the optimal prompt strategy, LLM model, and embedding model per query at run-time. This dynamic adaptation maximizes the efficacy of LLMs across languages, outperforming best static and random strategies. Additionally, our approach adapts configurations in both offline and online settings, and can seamlessly adapt to new languages and datasets, leading to substantial advancements in multilingual understanding and generation across diverse languages.