Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models

TL;DR

This survey reviews how large language models are used for context-aware machine translation, highlighting current methods, performance differences, and future research directions.

Contribution

It provides a comprehensive overview of existing LLM-based context-aware translation methods and compares commercial and open-source models.

Findings

Commercial LLMs outperform open-source models in translation quality

Prompt-based approaches serve as effective baselines

Few works focus on automatic post-editing and translation agents

Abstract

Despite the popularity of the large language models (LLMs), their application to machine translation is relatively underexplored, especially in context-aware settings. This work presents a literature review of context-aware translation with LLMs. The existing works utilise prompting and fine-tuning approaches, with few focusing on automatic post-editing and creating translation agents for context-aware machine translation. We observed that the commercial LLMs (such as ChatGPT and Tower LLM) achieved better results than the open-source LLMs (such as Llama and Bloom LLMs), and prompt-based approaches serve as good baselines to assess the quality of translations. Finally, we present some interesting future directions to explore.