In this paper we present a step-by-step approach to long-form text translation, drawing on established processes in translation studies. Instead of viewing machine translation as a single, monolithic task, we propose a framework that engages language models in a multi-turn interaction, encompassing pre-translation research, drafting, refining, and proofreading, resulting in progressively improved translations. Extensive automatic evaluations using Gemini 1.5 Pro across ten language pairs show that translating step-by-step yields large translation quality improvements over conventional zero-shot prompting approaches and earlier human-like baseline strategies, resulting in state-of-the-art results on WMT2024.

翻译：本文提出了一种基于翻译学既定流程的长文本分步翻译方法。不同于将机器翻译视为单一整体任务，我们提出一个框架，使语言模型通过多轮交互参与翻译过程，涵盖译前研究、草拟、润色和校对环节，从而逐步提升译文质量。使用Gemini 1.5 Pro在十组语言对上进行的大规模自动评估表明，分步翻译方法相较于传统的零样本提示方法及早期类人基线策略，能显著提升翻译质量，在WMT2024评测中取得了最先进的成果。