publications

2025

1. LLM-based Translation for Latin: Summaries Improve Machine Translation

   Dominic P Fischer and Martin Volk

   In Proceedings of the Swiss Text Analytics Conference, May 2025

   Abs DOI PDF Poster

   

   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.

2. Name Consistency in LLM-based Machine Translation of Historical Texts

   Dominic P Fischer and Martin Volk

   In Proceedings of Machine Translation Summit XX: Volume 1, Jun 2025

   Abs DOI PDF Slides

   

   Large Language Models (LLMs) excel at translating 16th-century letters from Latin and Early New High German to modern English and German. While they perform well at translating well-known historical city names (eg, Lutetia–> Paris), their ability to handle person names (eg, Theodor Bibliander) or lesser-known toponyms (eg, Augusta Vindelicorum–> Augsburg) remains unclear. This study investigates LLM-based translations of person and place names across various frequency bands in a corpus of 16th-century letters. Our results show that LLMs struggle with person names, achieving accuracies around 60%, but perform better with place names, reaching accuracies around 90%. We further demonstrate that including a translation suggestion for the proper noun in the prompt substantially boosts accuracy, yielding highly reliable results.

2024

1. LLM-based Machine Translation and Summarization for Latin

   Martin Volk, Dominic P Fischer, Lukas Fischer, and 4 more authors

   In Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) at LREC/COLING 2024, May 2024

   Abs DOI PDF

   

   This paper presents an evaluation of machine translation for Latin. We tested multilingual Large Language Models, in particular GPT-4, on letters from the 16th century that are in Latin and Early New High German. Our experiments include translation and cross-language summarization for the two historical languages into modern English and German. We show that LLM-based translation for Latin is clearly superior to previous approaches. We also show that LLM-based paraphrasing of Latin paragraphs from the historical letters produces English and German summaries that are close to human summaries published in the edition.

2. LLM-based Translation Across 500 Years. The Case for Early New High German

   Martin Volk, Dominic P Fischer, Patricia Scheurer, and 2 more authors

   In Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024), Sep 2024

   Abs DOI PDF Poster

   

   The recently developed large language models (LLMs) show surprising translation capabilities for modern languages. In contrast, this paper investigates the ability of GPT-4 and Gemini to translate 500-year-old letters from Early New High German into modern German. We experiment with a corpus from the 16th century that is partly in Latin and partly in ENH-German. This corpus consists of more than 3000 letters that have been edited and annotated by experts from the Institute of Swiss Reformation Studies. We exploit their annotations for the evaluation of machine translation from ENH-German to German. Our experiments show that using the lexical footnotes by the editors in the prompts or directly injected into the text leads to high quality translations.