Article

Investigations on using Evidence-Based GraphRag Pipeline using LLM Tailored for USMLE Style Questions

2025-05-05

Abstract excerpt

The integration of evidence-based reasoning with retrieval-augmented generation (GraphRAG) holds great promise for enhancing large language model (LLM) question-answering (QA) capabilities. This research proposes a GraphRAG frame-work that improves the interpretability and reliability of LLM-generated answers in the medical domain. Our approach constructs a knowledge graph using Neo4j to represent UMLS medical ent...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 03972825-5778-58f8-a6d8-4a2406a1e615
DOI: 10.1101/2025.05.03.25325604

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Investigations on using Evidence-Based GraphRag Pipeline using LLM Tailored for USMLE Style QuestionsDOI 10.1101/2025.05.03.25325604Read

Queryome: Orchestrating Retrieval, Reasoning, and Synthesis across Biomedical LiteratureSemantic proximity Read

Enhancing LLM Accuracy and Reducing Hallucinations using Query Refinement Technique and Knowledge GraphsSemantic proximity Read

Small but Specialized: A Domain-Adapted Retrieval-Augmented LLM Outperforms Frontier Generalists in Pediatric and Adolescent GynecologySemantic proximity Read

Large Language Models and Medical Knowledge Grounding for Diagnosis PredictionSemantic proximity Read

Development and validation of Retrieval Augmented Generation (RAG) and GraphRAG for complex clinical casesSemantic proximity Read

QUEST-AI: A System for Question Generation, Verification, and Refinement using AI for USMLE-Style ExamsSemantic proximity Read

Medical HyperRAG: A Hypergraph-Enhanced Retrieval-Augmented Generation Framework for Clinical Question AnsweringSemantic proximity Read

AI-Powered Test Question Generation in Medical Education: The DailyMed ApproachSemantic proximity Read

RAGnosis: Retrieval-Augmented Generation for Enhanced Medical Decision MakingSemantic proximity Read

LLM-based generation of USMLE-style questions with ASPET/AMSPC knowledge objectives: All RAGs and no richesSemantic proximity Read

Can Large Language Models Detect Contradicted Biomedical Evidence? A Dual-Annotator Benchmark AuditSemantic proximity Read

Retrieval‑Augmented Clinical Question‑Answering System for Bariatric Surgery Built on the ASMBS Textbook: From Good to GreatSemantic proximity Read