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. Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process which might take preparatory steps to ensure high-quality translation. This work explores this possibility by proposing the MAPS framework, which stands for Multi-Aspect Prompting and Selection. Specifically, we enable LLMs first to analyze the given source sentence and induce three aspects of translation-related knowledge: keywords, topics, and relevant demonstrations to guide the final translation process. Moreover, we employ a selection mechanism based on quality estimation to filter out noisy and unhelpful knowledge. Both automatic (3 LLMs x 11 directions x 2 automatic metrics) and human evaluation (preference study and MQM) demonstrate the effectiveness of MAPS. Further analysis shows that by mimicking the human translation process, MAPS reduces various translation errors such as hallucination, ambiguity, mistranslation, awkward style, untranslated text, and omission. Source 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瞩目的能力，其熟练程度在某些方面已接近乃至超越人类智能水平。在众多技能中，LLMs的翻译能力备受关注。与仅关注源语言到目标语言映射的典型机器翻译不同，基于LLM的翻译有望模拟人类翻译过程——这一过程可能包含确保翻译质量的预备步骤。本研究通过提出MAPS（多维度提示与选择框架）探索这一可能性。具体而言，我们首先引导LLMs分析给定源句，诱导生成三类翻译相关知识：关键词、主题及相关示例，以指导最终翻译过程。同时，我们采用基于质量评估的选择机制，过滤噪声和无用知识。自动评估（3个LLMs × 11个方向 × 2项自动指标）与人工评估（偏好研究与MQM）均验证了MAPS的有效性。进一步分析表明，通过模拟人类翻译过程，MAPS能减少各类翻译错误，包括幻觉、歧义、误译、生硬风格、未译文本及漏译。源代码已发布于https://github.com/zwhe99/MAPS-mt。