面向中国古典诗歌翻译的大语言模型：基准构建、评估与改进
Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving
AI总结：
本文构建中国古典诗歌翻译基准PoetMT并提出基于GPT-4的评估指标，进而设计检索增强机器翻译方法RAT，实验证明其在自动指标和人工评估上均优于现有方法。
摘要：
与传统翻译任务不同，中国古典诗歌翻译要求在翻译具有文化和历史意义的内容时兼顾充分性与流畅性，并体现语言的诗意典雅。具备出色多语言能力的大语言模型（LLMs）可能为实现这一极高翻译要求带来一线希望。本文首先引入了一个合适的基准（PoetMT），其中每首中文诗歌都配有公认的典雅译文。同时，我们提出了一种基于GPT-4的新指标，用于评估当前大语言模型在多大程度上能够满足这些要求。我们的实证评估表明，现有的大语言模型在这一具有挑战性的任务中表现不足。因此，我们提出了一种检索增强机器翻译（RAT）方法，该方法融入与古典诗歌相关的知识，以推进大语言模型对中国诗歌的翻译。实验结果表明，在广泛使用的BLEU、COMET、BLEURT、我们提出的指标以及人工评估上，RAT一致优于所有对比方法。
英文摘要：
Different from the traditional translation tasks, classical Chinese poetry translation requires both adequacy and fluency in translating culturally and historically significant content and linguistic poetic elegance. Large language models (LLMs) with impressive multilingual capabilities may bring a ray of hope to achieve this extreme translation demand. This paper first introduces a suitable benchmark (PoetMT) where each Chinese poetry has a recognized elegant translation. Meanwhile, we propose a new metric based on GPT-4 to evaluate the extent to which current LLMs can meet these demands. Our empirical evaluation reveals that the existing LLMs fall short in the challenging task. Hence, we propose a Retrieval-Augmented Machine Translation (RAT) method which incorporates knowledge related to classical poetry for advancing the translation of Chinese Poetry in LLMs. Experimental results show that RAT consistently outperforms all comparison methods regarding wildly used BLEU, COMET, BLEURT, our proposed metric, and human evaluation.
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。
