Normative diagrams are a legal visualisation method with promising applications within legal practice, legal theory, and especially for the didactics of law. The paper at hand presents the implementation of ViNo, a legal visualisation tool (including a graphical user interface) based on this method.

We automatically create summaries (guiding principles) of German judgments by fine-tuning a decoder-based large language model and 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. Our results show that employing legal entities helps the model to find relevant content, but the quality of the created summaries is not yet sufficient for a use in practice.

The legal visualisation method of normative diagrams is a powerful tool to visualise legal norms. However, a major limitation of normative diagrams in their original form is their sole focus on visualising norms regulating human behaviour. The paper at hand proposes to extend the framework of normative diagrams by adding validity diagrams, which may illustrate the validity of the behaviour norms already incorporated in normative diagrams in their original form. This extension further enhances the capabilities of normative diagrams and allows for a thorough visualisation, e.g. of conditional norms and legal if… then… structures. By providing different visualisations for different kinds of normative conditions, the improved method of normative diagrams presented here also contributes to clarifying the differences between various types of conditional norms.

Normative diagrams are a legal visualisation method with promising didactic, theoretical and practical applications. The paper at hand introduces the first implementation of a legal visualisation tool based on this method, discusses its limitations and refers to future work.

ROUGE is the most commonly used measure for evaluating summarization algorithms in practice. However, it is questionable whether ROUGE scores adequately reflect the quality of summaries in terms of content. We introduce a metric to measure (legal) content of summaries based on exhaustiveness and concreteness and compare ROUGE scores with values generated by legal experts according to our metric on two tasks. Our results show that ROUGE does not reliably gauge legal content and thus should not be used as a single indicator for the quality of summarization algorithms. For our particular use case we furthermore show one way to increase the reliability of ROUGE by pre-selecting sentences.

Legal text summarization focuses on the automated creation of summaries for legal texts. We show that the argumentative structure of judgments can improve the selection of guiding principles as a specific kind of summary using judgments of the German Federal Court of Justice as measured by the ROUGE metric. We evaluate our first results and put them in the context of our ongoing work.