Highlight
Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization
A generative AI system integrating Retrieval-Augmented Generation, Vector Stores, and Knowledge Graphs for legal information retrieval.
Based on
By Ryan Calvin Barron, Maksim E. Eren, Olga M. Serafimova, Cynthia Matuszek, Boian Alexandrov
Read original article →The paper presents a jurisdiction-specific legal information retrieval system that combines Retrieval-Augmented Generation, Vector Stores, and Knowledge Graphs constructed via Hierarchical Non-Negative Matrix Factorization.
The system is designed to enhance information retrieval and AI reasoning in the legal domain, minimizing hallucinations. It empowers AI agents to identify complex connections among cases, statutes, and legal precedents.
Share
Take the next step
Try CoreModels, talk with our team, or explore more resources.