AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts

TL;DR

This paper introduces AGB-DE, a new annotated corpus of German consumer contract clauses, and evaluates baseline models for detecting potentially void clauses, highlighting the task's complexity and interpretative challenges.

Contribution

The paper presents the first annotated dataset for legal clause assessment in German contracts and benchmarks multiple models, including GPT-3.5, for clause validity detection.

Findings

No model exceeded an F1-score of 0.54.

GPT-3.5 achieved the best recall among models.

Complex clause interpretation is a key challenge.

Abstract

Legal tasks and datasets are often used as benchmarks for the capabilities of language models. However, openly available annotated datasets are rare. In this paper, we introduce AGB-DE, a corpus of 3,764 clauses from German consumer contracts that have been annotated and legally assessed by legal experts. Together with the data, we present a first baseline for the task of detecting potentially void clauses, comparing the performance of an SVM baseline with three fine-tuned open language models and the performance of GPT-3.5. Our results show the challenging nature of the task, with no approach exceeding an F1-score of 0.54. While the fine-tuned models often performed better with regard to precision, GPT-3.5 outperformed the other approaches with regard to recall. An analysis of the errors indicates that one of the main challenges could be the correct interpretation of complex clauses, rather than the decision boundaries of what is permissible and what is not.