Knowledge Tree
MedRAG
Facts (14)
Sources
Medical Hallucination in Foundation Models and Their ... medrxiv.org Mar 3, 2025 4 facts
referenceMedRAG is a systematic toolkit designed for medical question answering that combines multiple medical datasets with diverse retrieval techniques to improve LLM performance in clinical tasks, as described by Xiong et al. (2024b).
referenceMedRAG (Xiong et al., 2024a) is a retrieval-augmented generation model designed for the medical domain that utilizes a knowledge graph to enhance reasoning capabilities.
procedureTo ground Large Language Model responses in validated medical information, the authors used MedRAG to retrieve relevant medical knowledge from a knowledge graph for each Med-HALT question and concatenated this knowledge with the original question as input to the Large Language Model.
procedureThe Med-HALT benchmark evaluation procedure for embedding generation involves encoding the original medical question, the correct ground truth option, and the model's generated output for each method (Base, System Prompt, CoT, MedRAG, Internet Search) into embeddings using UMLSBERT.
Medical Hallucination in Foundation Models and Their Impact on ... medrxiv.org Nov 2, 2025 3 facts
procedureThe Similarity Score calculation process involves three steps: (1) Embedding Generation: Encoding the original medical question, the correct option, and the model's generated output using UMLSBERT for each method (Base, System Prompt, CoT, MedRAG, Internet Search). (2) Cosine Similarity Calculation: Calculating the cosine similarity for model outputs against the correct option (Answer Similarity) and the original question (Question Similarity). (3) Combined Similarity Score: Computing the average of the Answer Similarity and the Question Similarity.
claimThe authors of the study adapted the publicly available MedRAG code and its associated knowledge graph to enable Large Language Models to generate responses grounded in external, validated medical information.
procedureThe 'RAG' (Retrieval-Augmented Generation) evaluation method employs MedRAG [224], a model designed for the medical domain that utilizes a knowledge graph to retrieve relevant medical knowledge and concatenate it with the original question before inputting it to the LLM.
Bridging the Gap Between LLMs and Evolving Medical Knowledge arxiv.org Jun 29, 2025 2 facts
measurementThe AMG-RAG system configured with the PubMed-MKG and an 8B LLM backbone achieves an accuracy of 73.92% on the MEDQA benchmark, surpassing baseline models including Self-RAG (Asai et al., 2023), HyDE (Gao et al., 2022), GraphRAG (Edge et al., 2024), and MedRAG (Zhao et al., 2025).
referenceXuejiao Zhao et al. (2025) published 'Medrag: Enhancing retrieval-augmented generation with knowledge graph-elicited reasoning for healthcare copilot' as an arXiv preprint (arXiv:2502.04413), which focuses on improving RAG with knowledge graphs.
Large Language Models Meet Knowledge Graphs for Question ... arxiv.org Sep 22, 2025 2 facts
claimXuejiao Zhao, Siyan Liu, Su-Yin Yang, and Chunyan Miao published the paper 'MedRAG: Enhancing retrieval-augmented generation with knowledge graph-elicited reasoning for healthcare copilot' in 2025.
referenceMedRAG, developed by Nanyang Technological University and other researchers, is a knowledge-graph-elicited, reasoning-enhanced, RAG-based healthcare copilot that generates medical diagnoses and treatment recommendations based on input patient manifestations.
Construction of intelligent decision support systems through ... - Nature nature.com Oct 10, 2025 2 facts
referenceFan et al. authored 'MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot', published in the Proceedings of the ACM on Web Conference in 2025.
claimMedRAG combines knowledge graph-elicited reasoning with retrieval-augmented generation for healthcare applications.
LLM-KG4QA: Large Language Models and Knowledge Graphs for ... github.com 1 fact
referenceThe paper 'MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot' (WWW, 2025) proposes using knowledge graph-elicited reasoning to enhance retrieval-augmented generation for healthcare applications.