Administrative and legal communication is often difficult for laypersons to understand, creating barriers to justice and undermining trust in public institutions. The PONK tool helps authors identify and revise unclear text using a multimodular approach that combines linguistic rules and lexical surprisal based on large language models. This integration ensures precise and adaptable detection of problematic passages. Human evaluation confirmed the tool’s effectiveness in improving legal text comprehensibility. PONK’s user-friendly interface highlights unclear segments at the word level, offering a practical solution for clearer and more accessible legal communication.

Retrieving relevant case law remains a time-consuming task. We compare two embedding models for Czech Constitutional Court decisions: (i) a large general-purpose OpenAI embedder and (ii) a domain-specific BERT trained from scratch on ∼34,000 decisions. We introduce a noise-aware evaluation using IDF-weighted keyword overlap as graded relevance, dual thresholds (0.20, 0.28), paired-bootstrap significance, and nDCG diagnostics. Despite conservative absolute nDCG due to noisy institutional labels, the OpenAI embedder consistently and significantly outperforms the domain BERT across all ranks and thresholds. Our framework enables robust evaluation under imperfect gold standards typical of legacy judicial databases.

This paper analyses automated and human-driven evaluation approaches for Large Language Models (LLMs) performance in the legal domain, stressing the need to combine both into hybrid evaluation frameworks. This conclusion is reinforced by a qualitative case study that uncovers assessment factors considered by lawyers when using LLMs. The diverse nature of these factors, requiring distinct evaluation approaches, underscores the need for adopting a hybrid methodology.

We design a framework for assisted normative reasoning based on Aristotelian diagrams and algorithmic graph theory which can be employed to address heterogeneous tasks of deductive reasoning. Here we focus on two problems of normative determination: we show that the algorithms used to address these problems are computationally efficient and their operations are traceable by humans. Finally, we discuss an application of our framework to a scenario regulated by the GDPR.

In this paper, we examine the use of multi-lingual sentence embeddings to transfer predictive models for functional segmentation of adjudicatory decisions across jurisdictions, legal systems (common and civil law), languages, and domains (i.e. contexts). Mechanisms for utilizing linguistic resources outside of their original context have significant potential benefits in AI & Law because differences between legal systems, languages, or traditions often block wider adoption of research outcomes. We analyze the use of Language-Agnostic Sentence Representations in sequence labeling models using Gated Recurrent Units (GRUs) that are transferable across languages. To investigate transfer between different contexts we developed an annotation scheme for functional segmentation of adjudicatory decisions. We found that models generalize beyond the contexts on which they were trained (e.g., a model trained on administrative decisions from the US can be applied to criminal law decisions from Italy). Further, we found that training the models on multiple contexts increases robustness and improves overall performance when evaluating on previously unseen contexts. Finally, we found that pooling the training data from all the contexts enhances the models' in-context performance.

In this article, I present the results of the human evaluation experiment of three commonly used methods in legal information retrieval and a new “multilayered” approach. I use the doc2vec model, citation network analysis and two topic modelling algorithms for the Czech Supreme Court decisions retrieval and evaluate their performance. To improve the accuracy of the results of these methods, I combine the methods in a “multilayered” way and perform the subsequent evaluation. Both evaluation experiments are conducted with a group of legal experts to assess the applicability and usability of the methods for legal information retrieval. The combination of the doc2vec and citations is found satisfactory accurate for practical use for the Czech court decisions retrieval.