Cross-Lingual Optimization for Language Transfer in Large Language Models
This addresses the challenge of efficient language transfer for multilingual AI applications, though it appears incremental as it builds on existing fine-tuning methods with a novel optimization approach.
The paper tackles the problem of adapting large language models to other languages without overemphasizing English performance, particularly in data-constrained environments, by proposing Cross-Lingual Optimization (CLO), which outperforms supervised fine-tuning in target language proficiency and English preservation, achieving better results with less data, such as surpassing SFT with 6,400 samples using only 3,200 samples in low-resource languages.
Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in data-constrained environments. To overcome these challenges, we propose \textbf{Cross-Lingual Optimization (CLO)} that efficiently transfers an English-centric LLM to a target language while preserving its English capabilities. CLO utilizes publicly available English SFT data and a translation model to enable cross-lingual transfer. We conduct experiments using five models on six languages, each possessing varying levels of resource. Our results show that CLO consistently outperforms SFT in both acquiring target language proficiency and maintaining English performance. Remarkably, in low-resource languages, CLO with only 3,200 samples surpasses SFT with 6,400 samples, demonstrating that CLO can achieve better performance with less data. Furthermore, we find that SFT is particularly sensitive to data quantity in medium and low-resource languages, whereas CLO remains robust. Our comprehensive analysis emphasizes the limitations of SFT and incorporates additional training strategies in CLO to enhance efficiency.