Computer Science / Artificial Intelligence

Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation

Reading time: 1 minute
...

📝 Original Info

  • Title: Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation
  • ArXiv ID: 2601.01844
  • Date: 2026-01-05
  • Authors: Udiptaman Das, Krishnasai B. Atmakuri, Duy Ho, Chi Lee, Yugyung Lee

📝 Abstract

Large language models (LLMs) offer new opportunities for constructing knowledge graphs (KGs) from unstructured clinical narratives. However, existing approaches often rely on structured inputs and lack robust validation of factual accuracy and semantic consistency-limitations that are especially problematic in oncology. We introduce an end-to-end framework for clinical KG construction and evaluation from free text using multi-agent prompting and a schema-constrained Retrieval-Augmented Generation (KG-RAG) strategy. Our pipeline integrates: (1) prompt-driven entity, attribute, and relation extraction; (2) entropy-based uncertainty scoring; (3) ontology-aligned RDF/OWL schema generation; and (4) multi-LLM consensus validation for hallucination detection and semantic refinement. Beyond static construction, the framework supports continuous refinement and self-supervised evaluation to iteratively improve graph quality. Applied to two oncology cohorts (PDAC and BRCA), our method produces interpretable, SPARQL-compatible, and clinically grounded knowledge graphs without goldstandard annotations, achieving consistent gains in precision, relevance, and ontology compliance over baseline methods.

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)

Start searching

Enter keywords to search articles

↑↓
↵
ESC
⌘K Shortcut