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.
@article{arxiv.2506.07583,
title = {Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models},
author = {Ramakrishna Appicharla and Baban Gain and Santanu Pal and Asif Ekbal},
journal= {arXiv preprint arXiv:2506.07583},
year = {2025}
}