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

arXiv: https://arxiv.org/abs/2305.17740 · HTML: https://mlsanity.com/paper/2305.17740/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 28 May 2023.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [MLQA: Evaluating Cross-lingual Extractive Question Answering](https://mlsanity.com/paper/1910.07475/) (2019)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [Larger-Scale Transformers for Multilingual Masked Language Modeling](https://mlsanity.com/paper/2105.00572/) (2021)
- [Balancing Training for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2004.06748/) (2020)
- [Discrete and Soft Prompting for Multilingual Models](https://mlsanity.com/paper/2109.03630/) (2021)
- [Learning Language Representations for Typology Prediction](https://mlsanity.com/paper/1707.09569/) (2017)
- [Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt](https://mlsanity.com/paper/2202.11451/) (2022)
- [Prompt Tuning for Generative Multimodal Pretrained Models](https://mlsanity.com/paper/2208.02532/) (2022)
- [Do Multilingual Language Models Capture Differing Moral Norms?](https://mlsanity.com/paper/2203.09904/) (2022)
- [Learning to Reconstruct Confocal Microscopy Stacks from Single Light Field Images](https://mlsanity.com/paper/2003.11004/) (2020)

## Built on by (most cited first, 8 of 8)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Language Specific Knowledge: Do Models Know Better in X than in English?](https://mlsanity.com/paper/2505.14990/) (2025)
- [Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?](https://mlsanity.com/paper/2402.13917/) (2024)
- [Anecdoctoring: Automated Red-Teaming Across Language and Place](https://mlsanity.com/paper/2509.19143/) (2025)
- [Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.14896/) (2026)
- [SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models](https://mlsanity.com/paper/2406.18880/) (2024)
- [CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.25182/) (2026)
- [Phishing Email Detection Using Large Language Models](https://mlsanity.com/paper/2512.10104/) (2025)

## Abstract (arXiv)

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.