CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification

TL;DR

CuraView is a multi-agent framework that enhances the detection of hallucinations in medical discharge summaries by leveraging graph-based knowledge verification, significantly improving factual reliability in clinical documentation.

Contribution

The paper introduces CuraView, a novel multi-agent system utilizing GraphRAG for evidence-grounded hallucination detection in EHRs, with improved accuracy over existing methods.

Findings

Achieved an F1 score of 0.831 on E4 hallucination detection.

Outperformed baseline models by 50% in relative F1 score improvement.

Produced structured evidence chains that improve interpretability and reliability.

Abstract

Discharge summaries require extracting critical information from lengthy electronic health records (EHRs), a process that is labor-intensive when performed manually. Large language models (LLMs) can improve generation efficiency; however, they are prone to producing faithfulness hallucinations, statements that contradict source records, posing direct risks to patient safety. To address this, we present CuraView, a multi-agent framework for sentence-level detection and evidence-grounded explanation of faithfulness hallucinations in discharge summaries. CuraView constructs a GraphRAG-based knowledge graph from patient-level EHRs and implements a closed-loop generation-detection pipeline with sentence-level evidence retrieval and classification spanning four evidence grades from strong support to direct contradiction (E1-E4), yielding structured and interpretable evidence chains. We evaluate CuraView on a subset of 250 patients from the Discharge-Me benchmark, with 50 patients held out for testing. Our fine-tuned Qwen3-14B detection model achieves an F1 of 0.831 on the safety-critical E4 metric (90.9% recall, 76.5% precision) and an F1 of 0.823 on E3+E4, representing a 50.0% relative improvement over the base model and outperforming RAGTruth-style and QAGS-style baselines. These results demonstrate that evidence-chain-based graph retrieval verification substantially improves the factual reliability of clinical documentation, while simultaneously producing reusable annotated datasets for downstream model training and distillation.