让大模型先学目标语言的表达习惯，再翻译更自然。
Paraphrase-Aligned Machine Translation
- 先用句式改写训练大模型，使其模仿目标语言结构
- 在资源丰富和稀缺场景下都提升翻译质量
- 小模型效果接近甚至超过更大模型，适合资源有限场景
大型语言模型在机器翻译中表现出显著能力，但其生成结果有时与母语者常用表达存在偏差，这通常源于语言系统间句式差异。为此，我们提出ParaAlign Translator方法，通过微调大模型进行句子改写，使其句式结构与目标语言系统对齐，从而提升后续翻译表现。实验表明，该方法显著提升了LLaMA-3-8B模型在资源丰富和低资源场景下的翻译性能，效果达到甚至超越更大的LLaMA-3-70B模型。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated significant capabilities in machine translation. However, their translation quality is sometimes questioned, as the generated outputs may deviate from expressions typically used by native speakers. These deviations often arise from differences in sentence structure between language systems. To address this issue, we propose ParaAlign Translator, a method that fine-tunes LLMs to paraphrase sentences, aligning their structures with those of the target language systems. This approach improves the performance of subsequent translations. Experimental results demonstrate that the proposed method enhances the LLaMA-3-8B model's performance in both resource-rich and low-resource scenarios and achieves parity with or surpassing the much larger LLaMA-3-70B model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。