On-the-Fly Fusion of Large Language Models and Machine Translation

arXiv:2311.08306v2 Announce Type: replace
Abstract: We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. We perform experiments on 4 language pairs (both directions) with varying data amounts. We find that a slightly weaker-at-translation LLM can improve translations of a NMT model, and ensembling with an LLM can produce better translations than ensembling two stronger MT models. We combine our method with various techniques from LLM prompting, such as in …

abstract arxiv cs.cl data fly fusion language language models large language large language models llm machine machine translation translation translations type