测试五模型在时间数字本地化上的表现，提示词嵌入规则效果最佳。
Analysis of Numerical Localisation in LLM Translations
- 将本地化规则写入提示词上下文提升准确性
- 相比直接翻译，准确率显著提高（具体数值未提）
- 适合需本地化处理的轻量级应用开发者
本文扩展了Tang等人（2025）关于数值翻译的研究，分析了五种大型语言模型（LLMs）在时间、数字和日期本地化方面的能力，而非传统翻译。所选模型均能在普通硬件上运行，并为每种模式建立基准质量。随后测试了三种提升准确性的策略。与Tang等人不同的是，研究发现，在所测试的LLMs中，将本地化原则嵌入提示词上下文，相比直接翻译或其他策略，能带来统计学上显著的准确率提升。
原文摘要 · Abstract (English)
The work of Tang et. al. (2025) on numerical translation is extended by analysing the capability of five large language models (LLMs) for the localisation of times, numbers, and dates instead of translation. Models were selected that could be loaded onto and run on commodity hardware and a baseline quality for each mode is computed, then three different strategies to improve on that accuracy were tested. In contrast to Tang et. al., it was discovered that on the tested LLMs, embedding the localisation principles into the prompt context provided a statistically significant improvement in accuracy compared to direct translation or the alternative strategies.
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。