<ul data-eligibleForWebStory="false"><li>Retrieval-Augmented Generation (RAG) aims to enhance language models by incorporating external information.</li><li>Knowledge graphs (KGs) are introduced in the KGRAG-Ex system to improve factual grounding and explainability.</li><li>KGRAG-Ex leverages a domain-specific KG to identify relevant entities and semantic paths for natural language generation.</li><li>The system incorporates perturbation-based explanation methods to assess the influence of KG-derived components on generated answers for improved interpretability.</li></ul>

KGRAG-Ex: Explainable Retrieval-Augmented Generation with Knowledge Graph-based Perturbations

Discover more