用树形结构选优质翻译样例，提升英译波斯语和德语质量
TreePrompt: Leveraging Hierarchical Few-Shot Example Selection for Improved English-Persian and English-German Translation
- 构建树状结构，结合上下文与样例质量筛选
- 在MIZAN和WMT19数据集上提升翻译效果
- 适合需要高质量少样本提示的机器翻译研究者
大型语言模型在机器翻译中表现优异，尤其在高质量提示引导下。少样本提示能有效提升翻译质量，但现有样例选择方法仅关注查询与样例的相似性，未考虑样例本身质量。本文提出TreePrompt，一种基于树形结构的新样例选择方法，通过学习语言模型偏好来识别高质量且上下文相关的样例。为探索相似性与质量间的平衡，将TreePrompt与K-NN及自适应少样本提示（AFSP）结合。在英译波斯语（MIZAN）和英译德语（WMT19）两个语对上的评估表明，TreePrompt与AFSP或随机选择结合后，翻译性能均有提升。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have consistently demonstrated strong performance in machine translation, especially when guided by high-quality prompts. Few-shot prompting is an effective technique to improve translation quality; however, most existing example selection methods focus solely on query-to-example similarity and do not account for the quality of the examples. In this work, we propose TreePrompt, a novel example selection approach that learns LLM preferences to identify high-quality, contextually relevant examples within a tree-structured framework. To further explore the balance between similarity and quality, we combine TreePrompt with K-Nearest Neighbors (K-NN) and Adaptive Few-Shot Prompting (AFSP). Evaluations on two language pairs - English-Persian (MIZAN) and English-German (WMT19) - show that integrating TreePrompt with AFSP or Random selection leads to improved translation performance.
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。