A Preference-driven Paradigm for Enhanced Translation with Large Language Models

arXiv:2404.11288v1 Announce Type: new
Abstract: Recent research has shown that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) using only a small amount of parallel data. However, SFT simply instructs the model to imitate the reference translations at the token level, making it vulnerable to the noise present in the references. Hence, the assistance from SFT often reaches a plateau once the LLMs have achieved a certain level of translation capability, and further increasing the …

abstract arxiv cs.cl data fine-tuning however language language models large language large language models llms making paradigm performance reference research sft small supervised fine-tuning through token translation translations type vulnerable