The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights

TL;DR

This paper demonstrates that applying question translation training, especially through question alignment, significantly enhances multilingual reasoning in large language models across various scenarios and sizes, with detailed analysis of underlying mechanisms.

Contribution

It extends question alignment training to diverse reasoning methods and large models, showing broad applicability and effectiveness in improving multilingual performance.

Findings

Average accuracy improvement of 12.2% on mGSM with LLaMA2-70B

Effective across reasoning scenarios and model sizes

Strengthens language alignment within LLMs

Abstract

Bridging the significant gap between large language model's English and non-English performance presents a great challenge. While some previous studies attempt to mitigate this gap with translated training data, the recently proposed question alignment framework leverages the model's English expertise to improve multilingual performance with minimum usage of expensive, error-prone translation. In this paper, we explore how broadly this method can be applied by examining its effects in reasoning with and without chain-of-thought, as well as with program-of-thought. We also explore applying this framework to extremely large language models in an efficient manner, such as through proxy-tuning. Experiment results on multilingual reasoning benchmarks mGSM, mSVAMP, xCSQA and xNLI demonstrate that we can extend question alignment framework to boost multilingual performance across diverse reasoning scenarios, model families, and sizes. For instance, when applied to the LLaMA2 models, it brings an average accuracy improvements of 12.2% on mGSM even with the 70B model. To understand the mechanism of its success, we analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs and shapes their working patterns.