Large language models (LLMs) demonstrate remarkable machine translation (MT) abilities via prompting, even though they were not explicitly trained for this task. However, even given the incredible quantities of data they are trained on, LLMs can struggle to translate inputs with rare words, which are common in low resource or domain transfer scenarios. We show that LLM prompting can provide an effective solution for rare words as well, by using prior knowledge from bilingual dictionaries to provide control hints in the prompts. We propose a novel method, DiPMT, that provides a set of possible translations for a subset of the input words, thereby enabling fine-grained phrase-level prompted control of the LLM. Extensive experiments show that DiPMT outperforms the baseline both in low-resource MT, as well as for out-of-domain MT. We further provide a qualitative analysis of the benefits and limitations of this approach, including the overall level of controllability that is achieved.
翻译:大型语言模型(LLMS)通过促进显示了非凡的机器翻译能力,尽管它们没有为此任务受过明确培训,但是,即使它们接受了惊人数量的数据培训,LLMS仍然能够用稀有文字翻译投入,这在低资源或域转移情景中是常见的。我们表明,LLMS的推广也可以为稀有文字提供有效的解决办法,利用来自双语词典的先前知识在提示时提供控制提示。我们提议了一种新颖的方法,DiPMT,它为输入的一组词提供了一套可能的翻译,从而能够对LLMM进行精细的语句级促动控制。 广泛的实验表明,DipMT在低资源MT和外部MT中都比基准都好。 我们还对这种方法的利弊和局限性,包括实现的总体控制水平,作了定性分析。