UniD$^3$: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and Reasoning
Researchers have developed UniD$^3$, a novel framework that combines Large Language Models with Knowledge Graph-enhanced Retrieval-Augmented Generation (KG-RAG) for drug-disease discovery. This system processes biomedical literature to build knowledge graphs, which then power KG-RAG for generating structured datasets and answering queries. UniD$^3$ has demonstrated strong performance in validating drug-disease relationships and outperforms standalone LLMs in evidence grounding. AI
IMPACT This framework could accelerate AI-driven drug discovery and precision medicine by improving the extraction and validation of drug-disease relationships from literature.