Multilingual Legislative Definitions Retrieval and Generation Using LLM and Agentic AI

Abstract

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.