Improving Machine Translation Capabilities by Fine-Tuning Large Language Models and Prompt Engineering with Domain-Specific Data
László János Laki, Zijian Győző Yang · 2024
This study examines the applicability and performance of large language models (LLMs) in the field of machine translation for in-domain texts, with a particular focus on fine-tuning LLMs, few-shot prompting, and word vector-based example sentence search methods. The aim of the study is to determine the extent to which the few-shot technique can improve translation quality for domain-specific texts. Our results indicate that the few-shot learning approach consistently improved translation quality across all examined LLM systems, with performance enhancements ranging from 10% to 25% in BLEU scores. Surprisingly, the word vector-based method, which uses the vectorial representation of words to select translation examples, did not perform as well as the character similarity-based fuzzy matching technique. The study discusses the performance of various systems, highlighting significant advancements achieved through fine-tuning and few-shot prompting.