LLM-based Translation for Latin: Summaries Improve Machine Translation

Abstract

Recent studies demonstrated that modern Large Language Models set a new state-of-the-art in translating historical Latin texts into English and German. Building upon this foundation, we investigate the impact of incorporating text summaries into prompts for LLM-based translation tasks. Having both the historical text and a modern-language summary is a typical setup for classical editions. Our findings reveal that integrating summaries significantly enhances translation accuracy and coherence.