A Service-Based Pipeline for Complex Linguistic Tasks Adopting LLMs and Knowledge Graphs

This paper introduces a microservices-based architecture de- signed for executing complex linguistic tasks using Large Language Mod- els (LLMs) and Knowledge Graphs (KGs). It has been conceived by fo- cusing on the legal domain, and it integrates Domain-specific KGs and Constraint KGs to address tasks such as law extraction and reasoning. We outline how the pipeline works through a running example involving the extraction of legislative references from legal documents. Further- more, we discuss a methodology for building KGs from unstructured documents and employing zero-shot prompt engineering techniques to facilitate information extraction. Finally, we present a validation process leveraging the Constraint KG to ensure the coherence and correctness of generated outputs.