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

arXiv:2405.01345v1 Announce Type: new
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 approach 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 executable code and reasoning with …

abstract alignment arxiv challenge cs.cl data english expertise gap insights language language model large language large language model multilingual performance power question reasoning studies training training data translated translation type while