Large language models (LLMs) have demonstrated impressive capabilities in general scenarios, exhibiting a level of aptitude that approaches, in some aspects even surpasses, human-level intelligence. Among their numerous skills, the translation abilities of LLMs have received considerable attention. In contrast to traditional machine translation that focuses solely on source-target mapping, LLM-based translation can potentially mimic the human translation process that takes many preparatory steps to ensure high-quality translation. This work aims to explore this possibility by proposing the MAPS framework, which stands for Multi-Aspect Prompting and Selection. Specifically, we enable LLMs to first analyze the given source text and extract three aspects of translation-related knowledge: keywords, topics and relevant demonstrations to guide the translation process. To filter out the noisy and unhelpful knowledge, we employ a selection mechanism based on quality estimation. Experiments suggest that MAPS brings significant and consistent improvements over text-davinci-003 and Alpaca on eight translation directions from the latest WMT22 test sets. Our further analysis shows that the extracted knowledge is critical in resolving up to 59% of hallucination mistakes in translation. Code is available at https://github.com/zwhe99/MAPS-mt.

翻译：大语言模型(LLMs)在通用场景中展现出令人印象深刻的能力，其水平在某些方面接近甚至超越人类智能。在众多技能中，LLMs的翻译能力受到了广泛关注。与仅关注源语言到目标语言映射的传统机器翻译不同，基于LLM的翻译可以模拟人类翻译过程，通过采取大量预备步骤来确保高质量翻译。本文旨在通过提出MAPS框架（多方位提示与选择）来探索这一可能性。具体而言，我们使LLM首先分析给定的源文本，提取三类翻译相关知识：关键词、主题和相关示例，以指导翻译过程。为过滤掉有噪声和无帮助的知识，我们采用基于质量估计的选择机制。实验表明，在最新WMT22测试集的八个翻译方向上，MAPS相较于text-davinci-003和Alpaca带来了显著且一致的改进。进一步分析显示，提取的知识在解决翻译中多达59%的幻觉错误方面至关重要。代码已开源至https://github.com/zwhe99/MAPS-mt。