Summarisation of German Judgments in conjunction with a Class-based Evaluation

Bianca Steffes, Nils Torben Wiedemann, Alexander Gratz, Pamela Hochreither, Jana Elina Meyer +1 more
5/9/2025
cs.CL

No official code found. Best implementation: bs-000/bgh-ls-llms-ler (0 stars, last commit 2025-05-07).

Abstract

The automated summarisation of long legal documents can be a great aid for legal experts in their daily work. We automatically create summaries (guiding principles) of German judgments by fine-tuning a decoder-based large language model. We enrich the judgments with information about legal entities before the training. For the evaluation of the created summaries, we define a set of evaluation classes which allows us to measure their language, pertinence, completeness and correctness. Our results show that employing legal entities helps the generative model to find the relevant content, but the quality of the created summaries is not yet sufficient for a use in practice.

View on arXivView PDF

Code Implementations(1)

bs-000/bgh-ls-llms-lerCommunity100%
00PythonMay 5, 20251 years ago

Similar Papers

Applicability of Large Language Models and Generative Models for Legal Case Judgement Summarization

86% match2024

Supporting Humans in Evaluating AI Summaries of Legal Depositions

82% match2 repos2026

Advantages of Domain Knowledge Injection for Legal Document Summarization: A Case Study on Summarizing Indian Court Judgments in English and Hindi

82% match2026

Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland

82% match2024

Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law

82% match2026

Low-Resource Court Judgment Summarization for Common Law Systems

82% match1 repo32024

Cite this paper

@article{steffes2025summarisation,
  title  = {Summarisation of German Judgments in conjunction with a Class-based Evaluation},
  author = {Bianca Steffes and Nils Torben Wiedemann and Alexander Gratz and Pamela Hochreither and Jana Elina Meyer and Katharina Luise Schilke},
  year   = {2025},
  eprint = {2505.05947},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.05947v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.05947.svg)](https://codeofpaper.com/paper/2505.05947)

Discussion