Search papers, labs, and topics across Lattice.
PharmGraph-Auditor is introduced, a system for prescription auditing that combines a hybrid pharmaceutical knowledge base (HPKB) with a knowledge-grounded Chain of Verification (CoV) reasoning paradigm. The HPKB unifies relational and graph components under a Virtual Knowledge Graph (VKG) paradigm, constructed using an Iterative Schema Refinement (ISR) algorithm for co-evolving schemas from medical texts. CoV transforms LLMs into transparent reasoning engines by decomposing the audit task into verifiable queries against the HPKB, improving safety and traceability in prescription verification.
By grounding LLMs in a hybrid knowledge base and using a Chain of Verification approach, PharmGraph-Auditor turns unreliable LLM generators into transparent reasoning engines for prescription auditing.
Medication errors pose a significant threat to patient safety, making pharmacist verification (PV) a critical, yet heavily burdened, final safeguard. The direct application of Large Language Models (LLMs) to this zero-tolerance domain is untenable due to their inherent factual unreliability, lack of traceability, and weakness in complex reasoning. To address these challenges, we introduce PharmGraph-Auditor, a novel system designed for safe and evidence-grounded prescription auditing. The core of our system is a trustworthy Hybrid Pharmaceutical Knowledge Base (HPKB), implemented under the Virtual Knowledge Graph (VKG) paradigm. This architecture strategically unifies a relational component for set constraint satisfaction and a graph component for topological reasoning via a rigorous mapping layer. To construct this HPKB, we propose the Iterative Schema Refinement (ISR) algorithm, a framework that enables the co-evolution of both graph and relational schemas from medical texts. For auditing, we introduce the KB-grounded Chain of Verification (CoV), a new reasoning paradigm that transforms the LLM from an unreliable generator into a transparent reasoning engine. CoV decomposes the audit task into a sequence of verifiable queries against the HPKB, generating hybrid query plans to retrieve evidence from the most appropriate data store. Experimental results demonstrate robust knowledge extraction capabilities and show promises of using PharmGraph-Auditor to enable pharmacists to achieve safer and faster prescription verification.
