PMMT：通过 LLM 蒸馏实现多语言机器翻译中的偏好对齐
PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
AI总结：
本文提出 PMMT 方法，利用 LLM 生成特定偏好语料并蒸馏至小模型，在偏好对齐翻译任务中大幅领先，且在 WMT 等基准上具竞争力。
摘要：
翻译对于跨语言交流很重要，人们已为提高其准确性做出了许多努力。然而，在将翻译与人类偏好（如翻译语气或风格）进行对齐方面，投入较少。本文提出了一种新方法，利用大型语言模型（LLMs）有效生成具有特定翻译偏好的大规模多语言平行语料库。同时，设计了一条自动化流水线，将人类偏好蒸馏到较小的机器翻译（MT）模型中，以高效且经济地支持在线服务中的大规模调用。实验表明，所提方法在人类偏好对齐的翻译任务中大幅领先。此外，在 WMT 和 Flores 等流行的公共基准（我们的模型未在这些基准上训练过）上，所提方法与 SOTA 工作相比也表现出有竞争力的性能。
英文摘要：
Translation is important for cross-language communication, and many efforts have been made to improve its accuracy. However, less investment is conducted in aligning translations with human preferences, such as translation tones or styles. In this paper, a new method is proposed to effectively generate large-scale multilingual parallel corpora with specific translation preferences using Large Language Models (LLMs). Meanwhile, an automatic pipeline is designed to distill human preferences into smaller Machine Translation (MT) models for efficiently and economically supporting large-scale calls in online services. Experiments indicate that the proposed method takes the lead in translation tasks with aligned human preferences by a large margin. Meanwhile, on popular public benchmarks like WMT and Flores, on which our models were not trained, the proposed method also shows a competitive performance compared to SOTA works.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
