发表机构
University of Florida（佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对WMT26低资源印度东北语言翻译任务，采用BM25检索示例、Gemini 2.5 Flash翻译的无微调方案，通过网格搜索确定最优参数，实现英语与11种印度东北语言的双向翻译。
AI 中文摘要
本文介绍了佛罗里达大学Gators团队提交给WMT26低资源印度语言翻译共享任务的方案。我们将AmericasNLP 2026系统中的检索增强多示例翻译流水线进行适配，用于英语与11种印度东北语言之间的双向翻译。推理阶段，BM25从特定语言的训练库中检索最相似的平行示例，Gemini 2.5 Flash在这些示例的条件下翻译输入，无需进行模型微调。训练库结合了官方WMT26数据与Samanantar等公开语料库及过往WMT共享任务发布的语料。我们在全部22种语言-方向对上对检索数量r和开发示例数量d进行网格搜索，为每个提交选择最优配置。
英文摘要
This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieval-augmented many-shot translation pipeline from our AmericasNLP 2026 system to translate between English and eleven North-Eastern Indian languages in both directions. At inference time, BM25 retrieves the most similar parallel examples from a language-specific training bank, and Gemini 2.5 Flash translates the input conditioned on these examples. No model fine-tuning is involved. Training banks combine official WMT26 data with publicly available corpora such as Samanantar and prior WMT shared task releases. A grid search over retrieval count r and development exemplar count d across all 22 language-direction pairs selects the best configuration for each submission.
