Paper · arXiv 2504.11833
Could Thinking Multilingually Empower LLM Reasoning?
Changjiang Gao, Xu Huang, Wenhao Zhu, Shujian Huang, Lei Li, Fei Yuan
Multilingual reasoning in large language models shows significant potential for improved performance in reasoning tasks compared to English-only models.
Abstract
Previous work indicates that large language models exhibit a significant "English bias", i.e. they often perform better when tasks are presented in English. Interestingly, we have observed that using certain other languages in reasoning tasks can yield better performance than English. However, this phenomenon remains under-explored. In this paper, we explore the upper bound of harnessing multilingualism in reasoning tasks, suggesting that multilingual reasoning promises significantly (by nearly 10 Acc@k points) and robustly (tolerance for variations in translation quality and language choice) higher upper bounds than English-only reasoning. Besides analyzing the reason behind the upper bound and challenges in reaching it, we also find that common answer selection methods cannot achieve this upper bound, due to their limitations and biases. These insights could pave the way for future research aimed at fully harnessing the potential of multilingual reasoning in LLMs.