Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Hallucinogens and Psychedelics

Hallucinogens and Psychedelics

Hallucinogens are psychoactive substances that profoundly alter perceptual experiences, generating unreal visual and sensory images. Often referred to as psychedelic drugs — a term derived from the Greek words "psyche" (mind) and "delos" (revealing) — these substances include marijuana and lysergic acid diethylamide (LSD), among others. These drugs vary in intensity and effects.
Marijuana, derived from the dried leaves and flowers of the hemp plant, contains...

CNS Stimulants: Psychedelic Agents

CNS Stimulants: Psychedelic Agents

Hallucinogens, also known as psychedelic drugs, are a class of substances known for their ability to alter perception, cognition, and emotions. Despite their profound effects on the mind, these drugs are non-addictive, setting them apart from many other abused substances. The mechanism of action of these drugs lies in their impact on the 5-HT2A receptor in the brain. Upon activation, this receptor couples to Gq-type G proteins, triggering a cascade that releases intracellular calcium. This...

Mnemonic Devices

Mnemonic Devices

Mnemonic devices are cognitive tools that facilitate memory retention by linking new information to familiar patterns or organizational strategies. These techniques are beneficial for remembering complex or lengthy sets of information by simplifying and structuring them in easily retrievable ways.
Acronyms
Acronyms are created by using the initial letters of a series of words to form a new word or phrase. This approach condenses complex information into a single, memorable entity. For example,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Sliding physical invariant neural operator for long-term prediction of complex dynamics in physical systems.

National science review·2026

Same author

Generation of gamma photons carrying transverse orbital angular momentum driven by a spatiotemporal optical vortex laser.

Optics express·2026

Same author

Diagnostic value of PRIMARY score and a combined model with SUVmax in 18F-PSMA-1007 PET/CT for prostate cancer.

Frontiers in medicine·2026

Same author

Worldwide research trends on the <i>Helicobacter pylori</i>-gut microbiome nexus: a bibliometric analysis.

Frontiers in immunology·2026

Same author

A multidimensional investigation of myelosuppression associated with sintilimab: integrating pharmacovigilance signal mining with real-world clinical evidence.

Frontiers in pharmacology·2026

Same author

Anesthetic management for thoracoscopic bilateral bullectomy in a patient with stage III pneumoconiosis, bilateral giant bullous emphysema, stage IV chronic obstructive pulmonary disease and profoundly impaired pulmonary function: a rare case report.

AME case reports·2026

Same journal

Forced changes in a Tibetan lake ecosystem over the past millennium.

Nature communications·2026

Same journal

Time-Temperature Superposition Principle Serving as a Design Tool for Tailored MOF-Crystal Glass Composite Membranes.

Nature communications·2026

Same journal

Simultaneous nanoscale imaging of local conductivity and chemical potential in a quantum Hall isospin ferromagnet.

Nature communications·2026

Same journal

A family of archaeal hibernation factors that bind in tandem and protect ribosomes in dormant cells.

Nature communications·2026

Same journal

Surface energy-driven perpendicular gradient structure in flexible composite dielectrics for high-temperature capacitive energy storage.

Nature communications·2026

Same journal

Severe droughts in Senegal are linked to increased family reunification at migration destinations in Europe.

Nature communications·2026

See all related articles

Search research articles

Home
Hyper-rag: Combating Llm Hallucinations Using Hypergraph-driven Retrieval-augmented Generation.

Home
Hyper-rag: Combating Llm Hallucinations Using Hypergraph-driven Retrieval-augmented Generation.

Related Experiment Video

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation.

Yifan Feng^1,2, Hao Hu^3,4, Shihui Ying⁵

¹{School of Software, BNRist, THUIBCS, BLBCI}, Tsinghua University, Beijing, China.

Nature Communications

|April 27, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

Hyper-RAG, a novel method for large language models (LLMs), significantly reduces factual errors in medical AI by capturing complex knowledge correlations. This enhances LLM reliability for critical applications.

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Related Experiment Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Area of Science:

Artificial Intelligence
Medical Informatics
Natural Language Processing

Background:

Large Language Models (LLMs) offer transformative potential across sectors, including medicine.
Medical LLM integration faces challenges due to "hallucinations"—inaccurate generated content posing risks.
Existing retrieval-augmented generation methods struggle with complex knowledge correlations.

Purpose of the Study:

To introduce Hyper-RAG, a hypergraph-driven Retrieval-Augmented Generation method.
To mitigate LLM hallucinations by capturing pairwise and beyond-pairwise knowledge correlations.
To enhance the reliability and accuracy of LLMs in high-stakes domains like medicine.

Main Methods:

Developed Hyper-RAG, utilizing hypergraphs to model intricate relationships in domain-specific knowledge.

Implemented a hypergraph-driven approach to augment LLM retrieval and generation processes.

Conducted experiments on the NeurologyCrop dataset and nine diverse datasets using prominent LLMs.

Main Results:

Hyper-RAG improved LLM accuracy by an average of 12.3% over direct use and outperformed GraphRAG (6.3%) and LightRAG (6.0%).
Hyper-RAG maintained stable performance with increasing query complexity, unlike other methods.
Hyper-RAG-Lite achieved double the retrieval speed and a 3.3% performance increase over LightRAG.

Conclusions:

Hyper-RAG effectively enhances LLM reliability and reduces hallucinations in medical applications.
The method demonstrates robustness across various datasets and query complexities.
Hyper-RAG presents a promising solution for safe and accurate AI in critical fields like medical diagnostics.