Question Translation Training for Better Multilingual Reasoning

Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch


Abstract
Large language models show compelling performance on reasoning tasks but they tend to perform much worse in languages other than English. This is unsurprising given that their training data largely consists of English text and instructions. A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training. This approach not only incurs high cost, but also results in poorly translated data due to the non-standard formatting of mathematical chain-of-thought. In this paper, we explore the benefits of question alignment, where we train the model to translate reasoning questions into English by finetuning on X-English parallel question data. In this way we perform targeted, in-domain language alignment which makes best use of English instruction data to unlock the LLMs’ multilingual reasoning abilities. Experimental results on LLaMA2-13B show that question alignment leads to consistent improvements over the translate-training approach: an average improvement of 11.3% and 16.1% accuracy across ten languages on the MGSM and MSVAMP multilingual reasoning benchmarks.
Anthology ID:
2024.findings-acl.498
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8411–8423
Language:
URL:
https://aclanthology.org/2024.findings-acl.498
DOI:
10.18653/v1/2024.findings-acl.498
Bibkey:
Cite (ACL):
Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, and Alexandra Birch. 2024. Question Translation Training for Better Multilingual Reasoning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 8411–8423, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Question Translation Training for Better Multilingual Reasoning (Zhu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.498.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.498.mp4