Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions

Jiahuan Li, Hao Zhou, Shujian Huang, Shanbo Cheng, Jiajun Chen


Abstract
Large-scale pretrained language models (LLMs), such as ChatGPT and GPT4, have shown strong abilities in multilingual translation, without being explicitly trained on parallel corpora. It is intriguing how the LLMs obtain their ability to carry out translation instructions for different languages. In this paper, we present a detailed analysis by finetuning a multilingual pretrained language model, XGLM-7.5B, to perform multilingual translation following given instructions. Firstly, we show that multilingual LLMs have stronger translation abilities than previously demonstrated. For a certain language, the translation performance depends on its similarity to English and the amount of data used in the pretraining phase. Secondly, we find that LLMs’ ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages. With multilingual finetuning with translation instructions, LLMs could learn to perform the translation task well even for those language pairs unseen during the instruction tuning phase.
Anthology ID:
2024.tacl-1.32
Volume:
Transactions of the Association for Computational Linguistics, Volume 12
Month:
Year:
2024
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
576–592
Language:
URL:
https://aclanthology.org/2024.tacl-1.32
DOI:
10.1162/tacl_a_00655
Bibkey:
Cite (ACL):
Jiahuan Li, Hao Zhou, Shujian Huang, Shanbo Cheng, and Jiajun Chen. 2024. Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions. Transactions of the Association for Computational Linguistics, 12:576–592.
Cite (Informal):
Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions (Li et al., TACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.tacl-1.32.pdf