AI RESEARCH
DrugRAG: Enhancing Pharmacy LLM Performance Through A Novel Retrieval-Augmented Generation Pipeline
arXiv CS.CL
•
ArXi:2512.14896v2 Announce Type: replace In our study, we evaluated large language model (LLM) performance on pharmacy licensure-style question-answering tasks and developed an external knowledge integration method to improve accuracy. We benchmarked ten LLMs with varying parameter sizes (8B to 70+ billion) using a 141-question pharmacy dataset, measuring baseline accuracy without modification. Baseline performance ranged from 46% to 92%, with GPT-5 (92%) and o3 (89%) achieving the highest scores, while smaller open-source models showed substantially lower performance.