mlsanityData to 7 Oct 2026

HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses

arXiv 2312.15883 ↗First posted 26 Dec 2023cs.CL cs.AIcited by 25

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs). Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. To this end, we develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework, which leverages LLMs' powerful reasoning capacity to compensate for the incompleteness of user queries, optimizes the interaction process with LLMs, and provides diverse retrieved knowledge. Specifically, HyKGE explores the zero-shot capability and the rich knowledge of LLMs with Hypothesis Outputs to extend feasible exploration directions in the KGs, as well as the carefully curated prompt to enhance the density and efficiency of LLMs' responses. Furthermore, we introduce the HO Fragment Granularity-aware Rerank Module to filter out noise while ensuring the balance between diversity and relevance in retrieved knowledge. Experiments on two Chinese medical multiple-choice question datasets and one Chinese open-domain medical Q&A dataset with two LLM turbos demonstrate the superiority of HyKGE in terms of accuracy and explainability.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 42 of its 86 references that are in the map. First posted on arXiv 26 Dec 2023.

Builds on

42 of 86 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  11. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  12. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
30 more
  1. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  2. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  3. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  4. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  6. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  7. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  8. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  9. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  10. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  11. 2023HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledgecited by 161
  12. 2023DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Taskcited by 130
  13. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  14. 2023Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialoguecited by 118
  15. 2023CMB: A Comprehensive Medical Benchmark in Chinesecited by 113
  16. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  17. 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
  18. 2021CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmarkcited by 99
  19. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  20. 2021Unified Named Entity Recognition as Word-Word Relation Classificationcited by 89
  21. 2023DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultationcited by 89
  22. 2023A Comprehensive Survey on Automatic Knowledge Graph Constructioncited by 63
  23. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54
  24. 2020SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Basescited by 47
  25. 2017Query expansion techniques for information retrieval: A surveycited by 44
  26. 2021UnitedQA: A Hybrid Approach for Open Domain Question Answeringcited by 42
  27. 2022Foresight -- Generative Pretrained Transformer (GPT) for Modelling of Patient Timelines using EHRscited by 11
  28. 2023Context-aware Decoding Reduces Hallucination in Query-focused Summarizationcited by 10
  29. 2023IvyGPT: InteractiVe Chinese pathwaY language model in medical domaincited by 9
  30. 2023Why Rumors Spread Fast in Social Networks, and How to Stop Itcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 10; 2026: 4.

25 papers.

Sort:

By area:

  1. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  3. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  4. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  5. 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 24
  6. 2024KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Modelscited by 20
  7. 2024Multi-Head RAG: Solving Multi-Aspect Problems with LLMscited by 18
  8. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  9. 2024Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuningcited by 14
  10. 2025Recurrent Knowledge Identification and Fusion for Language Model Continual Learningcited by 14
  11. 2026StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Managementcited by 13
  12. 2024Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generationcited by 12
13 more
  1. 2025GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigationcited by 11
  2. 2024ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphscited by 8
  3. 2025The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoningcited by 8
  4. 2025Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflectioncited by 6
  5. 20243DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selectioncited by 3
  6. 2025Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph Summarizationcited by 3
  7. 2024Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answeringcited by 2
  8. 2025DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Searchcited by 2
  9. 2026Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documentscited by 2
  10. 2026AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizingcited by 2
  11. 2025A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generationcited by 0
  12. 2025AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settingscited by 0
  13. 2026GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering
  2. 2025MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering
  3. 2026ReGraM: Region-First Knowledge Graph Reasoning for Medical Question Answering
  4. 2023Biomedical knowledge graph-optimized prompt generation for large language models
  5. 2025A Retrieval-Augmented Knowledge Mining Method with Deep Thinking LLMs for Biomedical Research and Clinical Support
  6. 2025Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
  7. 2026MedJudgeRAG: Option-Wise Evidence Judgment with Dynamic Knowledge Graphs for Medical MCQA
  8. 2025Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine