Automating translation checks of financial documents using large language models
We introduce a tool for automated translation checking of financial reports in German-English. It uses a heuristic matching algorithm followed by a transformer encoder based error detection model on sentence pair level. For generating the training data, we leverage state-of-the-art large language models such as {GPT}-4o, thereby alleviating the need for expert annotations. The results suggest that smaller models fine-tuned specifically for this task significantly outperform large multi-purpose generative models like {GPT}-4 for this particular problem, and that a combination of informed and deep learning approaches works best in this case. The tool is being made publicly available as a demonstrator.
- Veröffentlicht in:
Language Resources and Evaluation - Typ:
Article - Autoren:
- Jahr:
2025 - Source:
https://doi.org/10.1007/s10579-025-09862-z
Informationen zur Zitierung
: Automating translation checks of financial documents using large language models, Language Resources and Evaluation, 2025, July, https://doi.org/10.1007/s10579-025-09862-z, Pielka.etal.2025a,
@Article{Pielka.etal.2025a,
author={Pielka, Maren; Hahnbück, Max; Deußer, Tobias; Uedelhoven, Daniel; Chatterjee, Moinam; Shah, Vijul; Soliman, Osama; von der Bank, Jannis; Das, Writwick; Talarico, Maria Chiara; Zhao, Cong; Held Celis, Carolina; Temath, Christian; Sifa, Rafet},
title={Automating translation checks of financial documents using large language models},
journal={Language Resources and Evaluation},
month={July},
url={https://doi.org/10.1007/s10579-025-09862-z},
year={2025},
abstract={We introduce a tool for automated translation checking of financial reports in German-English. It uses a heuristic matching algorithm followed by a transformer encoder based error detection model on sentence pair level. For generating the training data, we leverage state-of-the-art large language models such as {GPT}-4o, thereby alleviating the need for expert annotations. The results suggest...}}
