Guardado en:
Detalles Bibliográficos
Autores principales: Nygren, Shad, Avci, Pinar, Daniels, Andre, Rassol, Reza, Beheshti, Afshin, Galeano, Diego
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.13822
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912490633297920
author Nygren, Shad
Avci, Pinar
Daniels, Andre
Rassol, Reza
Beheshti, Afshin
Galeano, Diego
author_facet Nygren, Shad
Avci, Pinar
Daniels, Andre
Rassol, Reza
Beheshti, Afshin
Galeano, Diego
contents Drug side effects are a major global health concern, necessitating advanced methods for their accurate detection and analysis. While Large Language Models (LLMs) offer promising conversational interfaces, their inherent limitations, including reliance on black-box training data, susceptibility to hallucinations, and lack of domain-specific knowledge, hinder their reliability in specialized fields like pharmacovigilance. To address this gap, we propose two architectures: Retrieval-Augmented Generation (RAG) and GraphRAG, which integrate comprehensive drug side effect knowledge into a Llama 3 8B language model. Through extensive evaluations on 19,520 drug side effect associations (covering 976 drugs and 3,851 side effect terms), our results demonstrate that GraphRAG achieves near-perfect accuracy in drug side effect retrieval. This framework offers a highly accurate and scalable solution, signifying a significant advancement in leveraging LLMs for critical pharmacovigilance applications.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13822
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAG-based Architectures for Drug Side Effect Retrieval in LLMs
Nygren, Shad
Avci, Pinar
Daniels, Andre
Rassol, Reza
Beheshti, Afshin
Galeano, Diego
Information Retrieval
Artificial Intelligence
Computation and Language
Drug side effects are a major global health concern, necessitating advanced methods for their accurate detection and analysis. While Large Language Models (LLMs) offer promising conversational interfaces, their inherent limitations, including reliance on black-box training data, susceptibility to hallucinations, and lack of domain-specific knowledge, hinder their reliability in specialized fields like pharmacovigilance. To address this gap, we propose two architectures: Retrieval-Augmented Generation (RAG) and GraphRAG, which integrate comprehensive drug side effect knowledge into a Llama 3 8B language model. Through extensive evaluations on 19,520 drug side effect associations (covering 976 drugs and 3,851 side effect terms), our results demonstrate that GraphRAG achieves near-perfect accuracy in drug side effect retrieval. This framework offers a highly accurate and scalable solution, signifying a significant advancement in leveraging LLMs for critical pharmacovigilance applications.
title RAG-based Architectures for Drug Side Effect Retrieval in LLMs
topic Information Retrieval
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2507.13822