mlsanityData to 7 Oct 2026

Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation

arXiv 2504.08758 ↗First posted 30 Mar 2025cs.IR cs.AIcited by 23

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

Large language models (LLMs) have transformed various sectors, including education, finance, and medicine, by enhancing content generation and decision-making processes. However, their integration into the medical field is cautious due to hallucinations, instances where generated content deviates from factual accuracy, potentially leading to adverse outcomes. To address this, we introduce Hyper-RAG, a hypergraph-driven Retrieval-Augmented Generation method that comprehensively captures both pairwise and beyond-pairwise correlations in domain-specific knowledge, thereby mitigating hallucinations. Experiments on the NeurologyCrop dataset with six prominent LLMs demonstrated that Hyper-RAG improves accuracy by an average of 12.3% over direct LLM use and outperforms Graph RAG and Light RAG by 6.3% and 6.0%, respectively. Additionally, Hyper-RAG maintained stable performance with increasing query complexity, unlike existing methods which declined. Further validation across nine diverse datasets showed a 35.5% performance improvement over Light RAG using a selection-based assessment. The lightweight variant, Hyper-RAG-Lite, achieved twice the retrieval speed and a 3.3% performance boost compared with Light RAG. These results confirm Hyper-RAG's effectiveness in enhancing LLM reliability and reducing hallucinations, making it a robust solution for high-stakes applications like medical diagnostics.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 49 references that are in the map. First posted on arXiv 30 Mar 2025.

Builds on

23 of 49 references.

References · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Qwen Technical Reportcited by 3,273
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  8. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  9. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  10. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 326
  11. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  12. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
11 more
  1. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  2. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  3. 2022Dense Text Retrieval based on Pretrained Language Models: A Surveycited by 136
  4. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 121
  5. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  6. 2023Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicinecited by 83
  7. 2021AI in Finance: Challenges, Techniques and Opportunitiescited by 81
  8. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 59
  9. 2023Opportunities for Retrieval and Tool Augmented Large Language Models in Scientific Facilitiescited by 27
  10. 2024RAGraph: A General Retrieval-Augmented Graph Learning Frameworkcited by 24
  11. 2020Trust and Medical AI: The challenges we face and the expertise needed to overcome themcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 20.

23 papers.

Sort:

By area:

  1. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 50
  2. 2026HyperMem: Hypergraph Memory for Long-Term Conversationscited by 14
  3. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generationcited by 3
  4. 2026Higher-Order Knowledge Representations for Agentic Scientific Reasoningcited by 3
  5. 2026HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAGcited by 3
  6. 2026Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systemscited by 1
  7. 2026SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedgescited by 1
  8. 2025Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verificationcited by 0
  9. 2026RAG without Forgetting: Continual Query-Infused Key Memorycited by 0
  10. 2026IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memorycited by 0
  11. 2026Beyond Fine-Tuning: Robust Food Entity Linking under Ontology Drift with FoodOntoRAGcited by 0
  12. 2026MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teacherscited by 0
11 more
  1. 2026HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoningcited by 0
  2. 2026Construction of Knowledge Graph based on Language Modelcited by 0
  3. 2026Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systemscited by 0
  4. 2026Hypergraph as Languagecited by 0
  5. 2026HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAGcited by 0
  6. 2026Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answeringcited by 0
  7. 2026A Multi-Agent Framework for Zero-Dimensional Reduced-Order Model Planningcited by 0
  8. 2026Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrievalcited by 0
  9. 2026DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answeringcited by 0
  10. 2026SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedgescited by 0
  11. 2026HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
  2. 2025Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation
  3. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  4. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation
  5. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
  6. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
  7. 2024100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo
  8. 2024Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models