Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automating translation checks of financial documents using large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月18日

查看全文
  • Maren Pielka,
  • Max Hahnbück,
  • Tobias Deußer,
  • Daniel Uedelhoven,
  • Moinam Chatterjee,
  • Vijul Shah,
  • Osama Soliman,
  • Jannis von der Bank,
  • Writwick Das,
  • Maria Chiara Talarico,
  • Cong Zhao,
  • Carolina Held Celis,
  • Christian Temath,
  • Rafet Sifa

摘要

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.