研究人员开发了一种名为Lius的新翻译模型，专门用于改进古邦马来语等低资源语言的翻译。该模型采用了一种新颖的持续指令微调（CIT）方法，通过各种指令类型迭代训练模型。这种方法显著优于标准的指令微调模型以及现有的神经机器翻译（NMT）和多语言LLM模型，展示了一种克服平行数据稀缺限制的充满希望的方法。 AI
影响 增强了代表性不足语言的翻译能力，可能使信息和通信的获取更加广泛。
排序理由 该集群描述了一篇详细介绍低资源语言翻译新方法和模型的新学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.11786v1 Announce Type: new Abstract: Large Language Models (LLMs) offer new potential for translation tasks but often experience performance degradation when handling low-resource languages. To address this limitation, we propose an approach for fine-tuning LLMs on a l…
Large Language Models (LLMs) offer new potential for translation tasks but often experience performance degradation when handling low-resource languages. To address this limitation, we propose an approach for fine-tuning LLMs on a low-resource language, Kupang Malay. Our approach…
Continual Instruction Tuning enables effective fine-tuning of large language models for low-resource language translation, achieving superior performance compared to standard instruction tuning and multilingual models.