The reviewed record of science sign in
Pith

arxiv: 2504.08758 · v1 · pith:W4XEHVJO · submitted 2025-03-30 · cs.IR · cs.AI

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:W4XEHVJOrecord.jsonopen to challenge →

classification cs.IR cs.AI
keywords hyper-raghallucinationsgenerationlightperformanceaccuracycontentenhancing
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers

    cs.IR 2026-04 unverdicted novelty 7.0

    MisEdu-RAG builds concept and instance hypergraphs for two-stage retrieval of pedagogical knowledge and student errors, improving feedback quality on the MisstepMath benchmark by 10.95% token-F1 and up to 15.3% on res...

  2. Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems

    cs.IR 2026-04 unverdicted novelty 7.0

    Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.

  3. Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems

    cs.AI 2026-05 unverdicted novelty 6.0

    HEAR uses a stratified hypergraph ontology to orchestrate evidence-driven multi-hop reasoning over heterogeneous business systems, reaching 94.7% accuracy on supply-chain root-cause tasks with open-weight models.

  4. FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG

    cs.IR 2026-02 unverdicted novelty 6.0

    FlexStructRAG jointly constructs knowledge graphs, hypergraphs, and semantic clusters with dynamic partitioning to enable query-adaptive multi-granular retrieval that improves semantic scores over standard RAG baselin...

  5. Construction of Knowledge Graph based on Language Model

    cs.CL 2026-04 unverdicted novelty 3.0

    The paper surveys PLM-based knowledge graph construction and proposes the LLHKG framework claiming that lightweight LLMs achieve KG construction performance comparable to GPT-3.5.