A Hybrid Knowledge-Grounded Framework for Safety and Traceability in Prescription Verification

2026-03-11

AI Summary

This work addresses critical safety limitations of large language models (LLMs) in prescription auditing—namely factual unreliability, weak reasoning capabilities, and lack of traceability—by proposing PharmGraph-Auditor, a novel system that integrates relational and graph-structured pharmaceutical knowledge. Built upon a virtual knowledge graph paradigm, the system employs an iterative schema refinement algorithm to enable co-evolution of graph topology and relational schemas. It further introduces a knowledge-grounded Chain-of-Verification (CoV) reasoning mechanism, transforming LLMs into transparent, traceable, and constraint-aware reasoning engines. Experimental results demonstrate that PharmGraph-Auditor significantly enhances accuracy, safety, and interpretability in both medical knowledge extraction and complex prescription review, thereby effectively supporting pharmacists in high-stakes clinical decision-making.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

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.

Problem

• medication errors
• prescription verification
• large language models
• traceability
• patient safety

Innovation

• Hybrid Knowledge Base
• Virtual Knowledge Graph
• Iterative Schema Refinement
• Chain of Verification
• Prescription Auditing