Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?

arXiv:2404.14122v1 Announce Type: new
Abstract: Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality. In the current practice of fine-tuning large language models (LLMs) for translation, we revisit the importance of all these factors. We find that LLMs display strong translation capability after being fine-tuned on as few as 32 training instances, and that fine-tuning on a single translation direction effectively enables LLMs to translate …

abstract arxiv cs.cl current data diverse fine-tuning key language language models languages large language large language models llms machine machine translation multilingual practice quality success training training data translate translation type will