Large language models (LLM) have demonstrated their abilities to solve various natural language processing tasks through dialogue-based interactions. For instance, research indicates that LLMs can achieve competitive performance in offline machine translation tasks for high-resource languages. However, applying LLMs to simultaneous machine translation (SimulMT) poses many challenges, including issues related to the training-inference mismatch arising from different decoding patterns. In this paper, we explore the feasibility of utilizing LLMs for SimulMT. Building upon conventional approaches, we introduce a simple yet effective mixture policy that enables LLMs to engage in SimulMT without requiring additional training. Furthermore, after Supervised Fine-Tuning (SFT) on a mixture of full and prefix sentences, the model exhibits significant performance improvements. Our experiments, conducted with Llama2-7B-chat on nine language pairs from the MUST-C dataset, demonstrate that LLM can achieve translation quality and latency comparable to dedicated SimulMT models.

翻译：大规模语言模型（LLM）已展现出通过对话式交互解决各类自然语言处理任务的能力。例如，研究表明，LLM在高资源语言的离线机器翻译任务中能够取得具有竞争力的表现。然而，将LLM应用于同步机器翻译（SimulMT）仍面临诸多挑战，包括因解码模式差异导致的训练-推理不匹配问题。本文探讨了利用LLM进行同步机器翻译的可行性。在传统方法基础上，我们提出了一种简单而有效的混合策略，使LLM无需额外训练即可参与同步机器翻译。此外，通过对完整句子和前缀句子的混合数据进行监督微调（SFT），该模型展现出显著的性能提升。我们在MUST-C数据集的九个语言对上使用Llama2-7B-chat模型进行的实验表明，LLM能够达到与专用SimulMT模型相当的翻译质量和延迟水平。