# Adapting Large Language Models for Document-Level Machine Translation

**Authors:** Minghao Wu, Thuy-Trang Vu, Lizhen Qu, George Foster, Gholamreza Haffari  
**arXiv:** [2401.06468](https://arxiv.org/abs/2401.06468)  
**Date:** 2024-01-12  
**Summary page:** https://www.summarizepaper.com/fr/paper/2401.06468v1/

## Abstract

Large language models (LLMs) have made significant strides in various natural language processing (NLP) tasks. Recent research shows that the moderately-sized LLMs often outperform their larger counterparts after task-specific fine-tuning. In this work, we delve into the process of adapting LLMs to specialize in document-level machine translation (DocMT) for a specific language pair. Firstly, we explore how prompt strategies affect downstream translation performance. Then, we conduct extensive experiments with two fine-tuning methods, three LLM backbones, and 18 translation tasks across nine language pairs. Our findings indicate that in some cases, these specialized models even surpass GPT-4 in translation performance, while they still significantly suffer from the off-target translation issue in others, even if they are exclusively fine-tuned on bilingual parallel documents. Furthermore, we provide an in-depth analysis of these LLMs tailored for DocMT, exploring aspects such as translation errors, the scaling law of parallel documents, out-of-domain generalization, and the impact of zero-shot crosslingual transfer. The findings of this research not only shed light on the strengths and limitations of LLM-based DocMT models but also provide a foundation for future research in DocMT.