Pith. sign in

REVIEW 30 cited by

Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.04187 v2 pith:D7DZOZ2X submitted 2024-08-08 cs.CV

Junde Wu , Jiayuan Zhu , Yunli Qi , Jingkun Chen , Min Xu , Filippo Menolascina , Vicente Grau This is my paper · ORCID
classification cs.CV
keywords medicalgenerationgraphbenchmarksresponsesretrievalcapabilitiesconstruction
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce a novel graph-based Retrieval-Augmented Generation (RAG) framework specifically designed for the medical domain, called \textbf{MedGraphRAG}, aimed at enhancing Large Language Model (LLM) capabilities for generating evidence-based medical responses, thereby improving safety and reliability when handling private medical data. Graph-based RAG (GraphRAG) leverages LLMs to organize RAG data into graphs, showing strong potential for gaining holistic insights from long-form documents. However, its standard implementation is overly complex for general use and lacks the ability to generate evidence-based responses, limiting its effectiveness in the medical field. To extend the capabilities of GraphRAG to the medical domain, we propose unique Triple Graph Construction and U-Retrieval techniques over it. In our graph construction, we create a triple-linked structure that connects user documents to credible medical sources and controlled vocabularies. In the retrieval process, we propose U-Retrieval which combines Top-down Precise Retrieval with Bottom-up Response Refinement to balance global context awareness with precise indexing. These effort enable both source information retrieval and comprehensive response generation. Our approach is validated on 9 medical Q\&A benchmarks, 2 health fact-checking benchmarks, and one collected dataset testing long-form generation. The results show that MedGraphRAG consistently outperforms state-of-the-art models across all benchmarks, while also ensuring that responses include credible source documentation and definitions. Our code is released at: https://github.com/MedicineToken/Medical-Graph-RAG.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 30 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications

    cs.CR 2024-11 conditional novelty 7.0 of 10

    An agent-based black-box attack, CopyBreakRAG, progressively extracts over 70% of chunks from RAG knowledge bases by alternating curiosity-driven exploration with reasoning-based exploitation.

  2. Training-Free Token-Level Steering for LLM Personalized Co-Writing

    cs.CL 2026-08 conditional novelty 6.0 of 10

    A token-level, training-free steering framework that improves LLM personalized co-writing by mixing the base model's posterior with a kernel-density estimate from a small user dataset.

  3. Agents-K1: Towards Agent-native Knowledge Orchestration

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    Agents-K1 is an end-to-end pipeline with a multimodal parser, 4B GRPO-trained extractor, and agent CLI that builds scientific knowledge graphs from full papers and was run on 2.46 million documents to produce Scholar-KG.

  4. Active Learning for Neurosymbolic Program Synthesis

    cs.PL 2025-08 unverdicted novelty 6.0 of 10

    The abstract claims a new active learning technique, constrained conformal evaluation (tool SmartLabel), that finds the ground-truth program in 98% of benchmarks, but the delivered full text is a different paper, leav...

  5. HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways

    cs.CL 2025-08 conditional novelty 6.0 of 10

    A semi-automated pipeline turns clinical decision trees into 4,063 medical Q&A pairs with explicit reasoning paths, and early LLM benchmarks show models improve when given those paths.

  6. XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation

    cs.IR 2025-06 conditional novelty 6.0 of 10

    A visual analytics framework helps GraphRAG developers trace suspicious retrievals through graph construction and LLM invocation stages, with a user study suggesting faster, more accurate failure diagnosis than an exi...

  7. Leaps Beyond the Seen: Reinforced Reasoning Augmented Generation for Clinical Notes

    cs.CL 2025-06 conditional novelty 6.0 of 10

    ReinRAG uses reinforcement learning to select knowledge-graph reasoning paths, including deliberate leaps across semantic clusters, to help an LLM generate discharge instructions from sparse pre-admission clinical inf...

  8. DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

    cs.CL 2025-05 reject novelty 6.0 of 10

    Combining knowledge retrieval, analogous patient case retrieval, and iterative textual-gradient refinement improves medical RAG accuracy across Chinese, English, and French benchmarks.

  9. Harmonia: End-to-End RAG Serving Optimization

    cs.DC 2025-05 conditional novelty 6.0 of 10

    An end-to-end RAG serving framework that uses component-level batching, resource allocation, and runtime prioritization to improve throughput and reduce SLO violations.

  10. Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools

    cs.AI 2025-02 conditional novelty 6.0 of 10

    An agentic reasoning framework that adds web search, code execution, and knowledge-graph memory to an LLM, boosting performance on expert-level benchmarks close to proprietary deep research systems.

  11. KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

    cs.CL 2025-01 conditional novelty 6.0 of 10

    An agentic KBQA system using MCTS exploration and reward-filtered self-training reaches 78.5 F1 on GrailQA with 40 labeled examples plus unlabeled data, up from 48.5 for the previous low-resource method.

  12. A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models

    cs.IR 2025-07 conditional novelty 5.0 of 10

    QMKGF builds multi-path knowledge graph subgraphs from LLM-extracted entities, fuses the highest-scoring subgraph with query-relevant triples, and expands the query to improve RAG answer quality.

  13. Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A multi-agent GraphRAG framework with self-reflection improves LLM accuracy on knowledge graph question answering.

  14. RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval

    cs.AI 2025-05 conditional novelty 5.0 of 10

    RoleRAG combines entity normalization and boundary-aware graph retrieval to make LLM role-playing more faithful to the character and less prone to hallucination.

  15. InterFeat: A Pipeline for Finding Interesting Scientific Features

    q-bio.QM 2025-05 conditional novelty 5.0 of 10

    InterFeat combines ML, knowledge graphs, PubMed, and LLMs to rank UK Biobank features by estimated scientific interestingness, with expert validation favoring it over SHAP-based feature lists.

  16. POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications

    cs.LG 2025-04 conditional novelty 5.0 of 10

    PolyRAG reranks retrieved medical documents by combining relevance, utility, supplement, authority, timeliness, and topic-composibility scores, and reports gains over standard retrievers on the new PolyEVAL benchmark.

  17. MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot

    cs.CL 2025-02 conditional novelty 5.0 of 10

    MedRAG combines retrieval-augmented generation with a hierarchical diagnostic knowledge graph to improve diagnostic accuracy in healthcare copilots.

  18. Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models

    cs.CV 2024-12 conditional novelty 5.0 of 10

    DiffEx explains classifier decisions by using a vision-language model to build a hierarchical semantic corpus and a beam-search algorithm to rank which visual attributes, alone or in combination, most influence classi...

  19. LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data

    cs.CV 2026-01 reject novelty 4.0 of 10

    A lightweight RGB-D cross-attention network is proposed for rail defect detection, but the SOTA accuracy and generalization claims are internally inconsistent and the implementation is not public.

  20. FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support

    cs.AI 2025-09 conditional novelty 4.0 of 10

    FHIR-RAG-MEDS integrates HL7 FHIR patient summaries into a RAG system and reports improved guideline-based recommendation quality over bare medical LLMs across four clinical domains.

  21. ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula

    cs.CL 2025-09 reject novelty 4.0 of 10

    A GraphRAG-plus-fine-tuning TCM formula generator outperforms baselines in its own experiments, but its theoretical proofs and evaluation are not sound.

  22. Continually Self-Improving Language Models for Bariatric Surgery Question--Answering

    cs.CL 2025-05 reject novelty 4.0 of 10

    bRAGgen uses a perplexity threshold to trigger web retrieval and LoRA fine-tuning, improving answers on a new bariatric surgery QA dataset, but the evaluation is confounded by test-time adaptation.

  23. OpenTCM: A GraphRAG-Empowered LLM-based System for Traditional Chinese Medicine Knowledge Retrieval and Diagnosis

    cs.IR 2025-04 conditional novelty 4.0 of 10

    OpenTCM combines an LLM-built TCM knowledge graph with GraphRAG to achieve high expert-rated accuracy in ingredient retrieval and diagnostic question answering.

  24. KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis

    cs.AI 2024-12 reject novelty 4.0 of 10

    A hierarchical multi-agent LLM framework with automatic knowledge graph construction for diagnosis across 362 diseases is proposed, but no evaluation is reported.

  25. A Retrieval-Augmented Generation Framework for Academic Literature Navigation in Data Science

    cs.IR 2024-12 conditional novelty 4.0 of 10

    A five-stage enhanced RAG pipeline for data science literature is reported to improve LLM-judged context relevance, though the evaluation is self-contained and not externally validated.

  26. Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method

    cs.CV 2026-01 reject novelty 3.0 of 10

    Fine-tuning Stable Diffusion with DreamBooth-style knowledge and hypernetwork-guided crack control maps can synthesize substation meter defect images that boost a YOLOv8 defect detector's mAP when added to the training set.

  27. A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods

    cs.CL 2025-01 conditional novelty 3.0 of 10

    A narrative review of LLM knowledge integration that categorizes techniques and compiles benchmarks, but lacks a systematic method and contains unreliable citations.

  28. A Survey on Retrieval And Structuring Augmented Generation with Large Language Models

    cs.CL 2025-09 conditional novelty 2.0 of 10

    The paper presents a comprehensive survey and taxonomy of RAS methods, covering retrieval, text structuring, and LLM integration.

  29. A Smart Multimodal Healthcare Copilot with Powerful LLM Reasoning

    cs.AI 2025-06 reject novelty 2.0 of 10

    A multimodal healthcare copilot using KG-elicited RAG is described, but the claimed superiority over existing systems is not demonstrated by the reported evaluation.

  30. Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers

    cs.IR 2025-05 conditional novelty 2.0 of 10

    A survey of retrieval-augmented generation methods, organized by architecture, with a comparative analysis of published QA results.

Pith tools