Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions
This work provides insights into LLM translation mechanisms, which is incremental for understanding and improving multilingual AI systems.
The paper investigates how multilingual large language models (LLMs) acquire translation abilities by finetuning XGLM-7B with translation instructions, finding that performance depends on language similarity to English and pretraining data, and that models can generalize to unseen language pairs.
Large-scale Pretrained Language Models (LLMs), such as ChatGPT and GPT4, have shown strong abilities in multilingual translations, without being explicitly trained on parallel corpora. It is interesting 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-7B, 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 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, LLMs could learn to perform the translation task well even for those language pairs unseen during the instruction tuning phase.