Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.10891 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908879324971008 |
|---|---|
| author | Zhu, Yichi Ling, Kan Liu, Xu Zhang, Hengrun Yu, Huiqun Fan, Guisheng |
| author_facet | Zhu, Yichi Ling, Kan Liu, Xu Zhang, Hengrun Yu, Huiqun Fan, Guisheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10891 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Hybrid Knowledge-Grounded Framework for Safety and Traceability in Prescription Verification Zhu, Yichi Ling, Kan Liu, Xu Zhang, Hengrun Yu, Huiqun Fan, Guisheng Artificial Intelligence Information Retrieval 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. |
| title | A Hybrid Knowledge-Grounded Framework for Safety and Traceability in Prescription Verification |
| topic | Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2603.10891 |