no code implementations • 20 May 2024 • Dean Allemang, Juan Sequeda
Our previous benchmark research showed that by using a knowledge graph, the accuracy improved from 16% to 54%.
no code implementations • 13 Nov 2023 • Juan Sequeda, Dean Allemang, Bryon Jacob
This study aims to evaluate the accuracy of LLM-powered question answering systems in the context of enterprise questions and SQL databases, while also exploring the role of knowledge graphs in improving accuracy.