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

arXiv: https://arxiv.org/abs/2605.03476 · HTML: https://mlsanity.com/paper/2605.03476/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 30 of 31)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Med-HALT: Medical Domain Hallucination Test for Large Language Models](https://mlsanity.com/paper/2307.15343/) (2023)
- [PMC-LLaMA: Towards Building Open-source Language Models for Medicine](https://mlsanity.com/paper/2304.14454/) (2023)
- [Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding](https://mlsanity.com/paper/2305.12031/) (2023)
- [Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning](https://mlsanity.com/paper/2505.00024/) (2025)
- [Lynx: An Open Source Hallucination Evaluation Model](https://mlsanity.com/paper/2407.08488/) (2024)
- [BioRAG: A RAG-LLM Framework for Biological Question Reasoning](https://mlsanity.com/paper/2408.01107/) (2024)
- [Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation](https://mlsanity.com/paper/2406.16678/) (2024)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (2025)
- [Overview of the First Shared Task on Clinical Text Generation: RRG24 and "Discharge Me!"](https://mlsanity.com/paper/2409.16603/) (2024)
- [RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models](https://mlsanity.com/paper/2411.00299/) (2024)
- [LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs](https://mlsanity.com/paper/2404.10933/) (2024)
- [Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization](https://mlsanity.com/paper/2503.01670/) (2025)
- [UF-HOBI at "Discharge Me!": A Hybrid Solution for Discharge Summary Generation Through Prompt-based Tuning of GatorTronGPT Models](https://mlsanity.com/paper/2407.15359/) (2024)
- [Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator](https://mlsanity.com/paper/2411.06465/) (2024)

## Built on by (most cited first, 1 of 1)

- [EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning](https://mlsanity.com/paper/2609.39371/) (2026)

## Abstract (arXiv)

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.