Automating translation checks of financial documents using large language models
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 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.
Authors
- Cong Zhao (ORCID: https://orcid.org/0000-0002-1017-9118)
- Tobias Deußer (ORCID: https://orcid.org/0000-0003-4685-0847)
- Rafet Sifa
- Jacob Bank
- Maria Talarico (ORCID: https://orcid.org/0000-0001-7901-5624)
- Maren Pielka (ORCID: https://orcid.org/0000-0001-9610-6026)
- Osama Soliman (ORCID: https://orcid.org/0000-0003-0758-3539)
- Daniel Uedelhoven
- Christian Temath (ORCID: https://orcid.org/0009-0001-2252-509X)
- Vijul Shah
- Moinam Chatterjee
- Carolina Held Celis
- Max Hahnbück
- Writwick Das
Institutions
- University of Bonn (DE)
- Fraunhofer Institute for Intelligent Analysis and Information Systems (DE)
Publication Details
- Journal
- Language Resources and Evaluation
- Published
- 2025-07-18
- DOI
- https://doi.org/10.1007/s10579-025-09862-z
- Citations
- 1
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Bundesministerium für Bildung und Forschung