Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation

arXiv:2405.10443v1 Announce Type: cross
Abstract: Large language models (LLMs) have achieved state-of-the-art performance in various language processing tasks, motivating their adoption in simultaneous translation. Current fine-tuning methods to adapt LLMs for simultaneous translation focus on prompting optimization strategies using either data augmentation or prompt structure modifications. However, these methods suffer from several issues, such as an unnecessarily expanded training set, computational inefficiency from dumping the KV cache, increased prompt sizes, or restriction to a single decision policy. To eliminate these …

abstract adapt adoption art arxiv augmentation cs.cl cs.lg current data fine-tuning focus language language models language processing large language large language models llms masking optimization paradigm performance processing prompt prompting shift state strategies tasks translation type