Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions

Understand

Existing large language models (LLMs) for machine translation are typically fine-tuned on sentence-level translation instructions and achieve satisfactory performance at the sentence level.

• However, when applied to document-level translation, these models face a significant challenge, particularly when dealing with documents containing over 512 tokens.
• This challenge arises from the issue of sentence-level coverage, where subsequent sentences in the document remain untranslated.
• As a result, the document-level translation capability of LLMs fine-tuned on sentence-level translation instructions is significantly limited.