Reporting requests in EU legislation require institutions to submit reports for legislative monitoring and policy implementation. As these meta-norms grow in complexity, compliance becomes increasingly challenging and burdensome. This paper leverages a Hybrid AI approach to detect, extract, and track reporting requests within the EU legislation using the RRVM ontology and European legal standards (AKN4EU, CELLAR, ELI). We investigate four interconnected and integrated areas: (1) detecting reporting requests and their concepts in legislative texts, (2) navigating normative references, (3) converting extracted legal knowledge into RDF for a Knowledge Graph, and (4) tracking modifications of reporting requests over time. Our approach compares machine learning (ML) and large language models (LLMs) for detection, demonstrating the advantages and limitations of both. By structuring Reporting Requests into a dynamic knowledge graph, our method improves the handling of Reporting Requests, reduces their administrative burden, and supports better legislative drafting and policy monitoring.

One of the most important legal assessments during legislative drafting proposals in Parliament is to check whether the bills have some provisions clashing with the Constitutional norms. Sometimes this situation is intentionally created by the proposer of a party to underline inconsistencies or incompleteness in the legal systems according to the reality of the society, but frequently, they are mistakes to avoid. This paper presents a method to calculate a multi-factor index of presumption of unconstitutionality of the provisions of a bill, to inform the proponent concerning a possible constitutional conflict. The paper uses a large dataset of bills, coming from the Chamber of Deputies of Italy, combined with Constitutional Court judgments and abstracts, EU and National legislation (9095 Italian laws, 3710 bills, 2979 judgments from the Constitutional Court). The methodology used is hybrid, considering different technological components, linked in a pipeline: i) embedding similarity; ii) normative references navigation; iii) semantic topic of the bill; iv) legislation cited in the judgments score based on the abrogated.

The application of AI-based methods and Large Language Models (LLMs) to the legislative domain poses unique challenges, including the extensive usage of normative references, the complexity of legal language, as well as the ever-changing nature of legal documents. We propose a multilingual (English-Italian) LLM-based method to both retrieve and generate legislative definitions in the context of the European and Italian legislation. These definitions are a crucial aspect of legislative documents, as they create new meaning for specific concepts, and their generation is an open challenge for any automatic method. New definitions should not conflict with pre-existing ones, be consistent with the specific legal domain (e.g., food, energy, finance), and instead leverage them when necessary. Our method fosters a Retrieval Augmented Generation approach, using LLM and Agentic AI, which considers the validity of existing definitions, the hierarchy of legal sources, and investigates strategies to mitigate hallucinations in the generation of definitions. We provide a quantitative and qualitative evaluation of the results of our experiments.

This paper presents classification tools to detect hate speech topics using NLP tools in four different languages (Italian, Spanish, Germany, English) using the selected case-law from national and international jurisdiction. The research is conducted inside the FAST-LISA European project with the aim to classify the hate speech in online public debate.

International Private Law (PIL) is a complex legal domain that presents frequent conflicting norms between the hierarchy of legal sources, legal domains, and the adopted procedures. Scientific research on PIL reveals the need to create a bridge between European and national laws. In this context, legal experts have to access heterogeneous sources, being able to recall all the norms and to combine them using case-laws and following the principles of interpretation theory. This clearly poses a daunting challenge to humans, whenever Regulations change frequently or are big-enough in size. Automated reasoning over legal texts is not a trivial task, because legal language is very specific and in many ways different from a commonly used natural language. When applying state-of-the-art language models to legalese understanding, one of the challenges is always to figure how to optimally use the available amount of data. This makes hard to apply state-of-the-art sub-symbolic question answering algorithms on legislative texts, especially the PIL ones, because of data scarcity. In this paper we try to expand previous works on legal question answering, publishing a larger and more curated dataset for the evaluation of automated question answering on PIL.

This paper presents an AI use-case developed in the project “Study on legislation in the era of artificial intelligence and digitization” promoted by the EU Commission Directorate-General for Informatics. We propose a hybrid technical framework where AI techniques, Data Analytics, Semantic Web approaches and LegalXML modelisation produce benefits in legal drafting activity. This paper aims to classify the corrigenda of the EU legislation with the goal to detect some criteria that could prevent errors during the drafting or during the publication process. We use a pipeline of different techniques combining AI, NLP, Data Analytics, Semantic annotation and LegalXML instruments for enriching the non-symbolic AI tools with legal knowledge interpretation to offer to the legal experts.

This study discusses the interplay between metrics used to measure the explainability of the AI systems and the proposed EU Artificial Intelligence Act. A standardisation process is ongoing: several entities (e.g. ISO) and scholars are discussing how to design systems that are compliant with the forthcoming Act and explainability metrics play a significant role. This study identifies the requirements that such a metric should possess to ease compliance with the AI Act. It does so according to an interdisciplinary approach, i.e. by departing from the philosophical concept of explainability and discussing some metrics proposed by scholars and standardisation entities through the lenses of the explainability obligations set by the proposed AI Act. Our analysis proposes that metrics to measure the kind of explainability endorsed by the proposed AI Act shall be risk-focused, model-agnostic, goal-aware, intelligible & accessible. This is why we discuss the extent to which these requirements are met by the metrics currently under discussion.

This paper presents a refinement of PrOnto ontology using a validation test based on legal experts’ annotation of privacy policies combined with an Open Knowledge Extraction algorithm. Three iterations were performed, and a final test using new privacy policies. The results are 75% of detection of concepts and relationships in the policy texts and an increase of 29% in the accuracy using the new refined version of PrOnto enriched with SKOSXL lexicon terms and definitions.