Scholarlink

Using the task of generating guiding principles for judgments of the German Federal Court of Justice we investigate whether current state of the art large language models can solve a complex legal summarisation task. Our results indicate that prompt engineering is not yet sufficient to solve the task, but fine-tuning already shows promising results. In addition, our results show that models with an increased context window size do not necessarily take the entire input into account equally.

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

Generating Guiding Principles: Evaluating Large Language Models for Complex German Legal Summaries

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Bianca Steffes,
  • Nils Torben Wiedemann

摘要

Using the task of generating guiding principles for judgments of the German Federal Court of Justice we investigate whether current state of the art large language models can solve a complex legal summarisation task. Our results indicate that prompt engineering is not yet sufficient to solve the task, but fine-tuning already shows promising results. In addition, our results show that models with an increased context window size do not necessarily take the entire input into account equally.