ClinicalRAG: Automating Pharmaceutical Label Quality Control with Hierarchical RAG and Large Language Models
Abstract
Every pharmaceutical product must be accompanied by a comprehensive label that delineates its indications, usage, dosages, and side effects, essential for safe medication practices. Traditionally, creating drug labels is labor-intensive and dependent on manual quality checks. Recent advancements in Large Language Models (LLMs) offer a promising avenue to streamline this process. In this paper we introduce ClinicalRAG, an automated labeling quality control pipeline that integrates LLM with hierarchical Retrieval Augmented Generation that allows to cross-check every statement in the drug label document. ClinicalRAG enhances the reliability of automated drug labeling by systematically reducing hallucination risks, achieving an accuracy of 96.1% in internal validation. With user-friendly interface, our pipeline aims to support pharmaceutical company in drug approval and expedite patients' access to new treatments.
Cite
Text
Zhou et al. "ClinicalRAG: Automating Pharmaceutical Label Quality Control with Hierarchical RAG and Large Language Models." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35384Markdown
[Zhou et al. "ClinicalRAG: Automating Pharmaceutical Label Quality Control with Hierarchical RAG and Large Language Models." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/zhou2025aaai-clinicalrag/) doi:10.1609/AAAI.V39I28.35384BibTeX
@inproceedings{zhou2025aaai-clinicalrag,
title = {{ClinicalRAG: Automating Pharmaceutical Label Quality Control with Hierarchical RAG and Large Language Models}},
author = {Zhou, Qiaohui and Zhou, Zhongliang and Johnson, Michael and Ngo, Michelle and Ferrari, Federico and Ma, Junshui},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {29736-29738},
doi = {10.1609/AAAI.V39I28.35384},
url = {https://mlanthology.org/aaai/2025/zhou2025aaai-clinicalrag/}
}