RAG-based Architectures for Drug Side Effect Retrieval in LLMs

• URL: http://arxiv.org/abs/2507.13822v1
• Date: Fri, 18 Jul 2025 11:20:52 GMT
• Title: RAG-based Architectures for Drug Side Effect Retrieval in LLMs
• Authors: Shad Nygren, Pinar Avci, Andre Daniels, Reza Rassol, Afshin Beheshti, Diego Galeano,
• Abstract summary: Large Language Models (LLMs) offer promising conversational interfaces, but their inherent limitations hinder their reliability in specialized fields like pharmacovigilance.<n>We propose two architectures: Retrieval-Augmented Generation (RAG) and GraphRAG, which integrate comprehensive drug side effect knowledge into a Llama 3 8B language model.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• DrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search [11.63163695551736]
  DrugMCTS is a novel framework that integrates RAG, multi-agent collaboration, and Monte Carlo Tree Search for drug repurposing.<n>DrugMCTS empowers Qwen2.5-7B-Instruct to outperform Deepseek-R1 by over 20%.<n>Our results highlight the importance of structured reasoning, agent-based collaboration, and feedback-driven search mechanisms.
  arXiv  Detail & Related papers  (2025-07-10T04:39:55Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery [54.79763887844838]
  Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution.<n>We introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific in drug discovery.<n>DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn scenarios, respectively.
  arXiv  Detail & Related papers  (2025-05-20T05:18:15Z)
• Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation [29.89840262866779]
  Large language models (LLMs) have transformed various sectors, including education, finance, and medicine, by enhancing content generation and decision-making processes.<n>However, their integration into the medical field is cautious due to hallucinations, instances where generated content deviates from factual accuracy, potentially leading to adverse outcomes.<n>We introduce Hyper-RAG, a hypergraph-driven Retrieval-Augmented Generation method that comprehensively captures both pairwise and beyond-pairwise correlations in domain-specific knowledge.
  arXiv  Detail & Related papers  (2025-03-30T12:39:14Z)
• GraPPI: A Retrieve-Divide-Solve GraphRAG Framework for Large-scale Protein-protein Interaction Exploration [13.390039857939168]
  Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks have accelerated drug discovery.<n>GraPPI is a large-scale knowledge graph (KG)-based retrieve-divide-solve agent pipeline RAG framework to support large-scale PPI signaling pathway exploration.
  arXiv  Detail & Related papers  (2025-01-24T18:16:53Z)
• Rx Strategist: Prescription Verification using LLM Agents System [0.0]
  Rx Strategist uses knowledge graphs and different search strategies to enhance the power of Large Language Models (LLMs) inside an agentic framework. This multifaceted technique allows for a multi-stage LLM pipeline and reliable information retrieval from a custom-built active ingredient database. Our findings demonstrate that Rx Strategist surpasses many current LLMs, achieving performance comparable to that of a highly experienced clinical pharmacist.
  arXiv  Detail & Related papers  (2024-09-05T11:42:26Z)
• Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation [64.7982176398485]
  Retrieval-augmented generation (RAG) has demonstrated effectiveness in mitigating the hallucination problem of large language models (LLMs) We propose DPA-RAG, a universal framework designed to align diverse knowledge preferences within RAG systems.
  arXiv  Detail & Related papers  (2024-06-26T18:26:53Z)
• A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction [85.2792480737546]
  Existing methods fail to utilize global protein information during DTI prediction. Cross-field information fusion strategy is employed to acquire local and global protein information. Siamese drug-target interaction SiamDTI prediction method achieves higher accuracy levels than other state-of-the-art (SOTA) methods on novel drugs and targets.
  arXiv  Detail & Related papers  (2024-05-23T13:25:20Z)
• CIDGMed: Causal Inference-Driven Medication Recommendation with Enhanced Dual-Granularity Learning [10.60553153370577]
  Medication recommendation aims to integrate patients' long-term health records to provide accurate and safe medication combinations. Existing methods often fail to deeply explore the true causal relationships between diseases/procedures and medications. We propose the Causal Inference-driven Dual-Granularity Medication Recommendation method (CIDGMed)
  arXiv  Detail & Related papers  (2024-03-01T08:50:27Z)
• SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction [127.43571146741984]
  Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery. wet experiments remain the most reliable method, but they are time-consuming and resource-intensive. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
  arXiv  Detail & Related papers  (2022-06-20T14:53:25Z)
• A standardized framework for risk-based assessment of treatment effect heterogeneity in observational healthcare databases [60.07352590494571]
  The aim of this study was to extend this approach to the observational setting using a standardized scalable framework. We demonstrate our framework by evaluating the effect of angiotensin-converting enzyme (ACE) inhibitors versus beta blockers on three efficacy and six safety outcomes.
  arXiv  Detail & Related papers  (2020-10-13T14:48:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.