Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
Estimation of k and VD of Aminoglycosides01:20

Estimation of k and VD of Aminoglycosides

Aminoglycosides are a class of antibiotics used to treat various bacterial infections. Clinicians must determine the elimination rate constant (k) and volume of distribution (VD) to optimize therapeutic efficacy and minimize toxicity. The k value represents the rate at which the drug is removed from the body, and the VD reflects the degree to which the drug distributes into body tissues. Accurately estimating these parameters allows healthcare professionals to tailor drug dosing to individual...

You might also read

Related Articles

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

Sort by
Same author

Protective potential of hydroxysafflor yellow A in cerebral ischemia and reperfusion injury: An overview of evidence from experimental studies.

Frontiers in pharmacology·2023
Same author

Transcriptome analysis reveals key drought-stress-responsive genes in soybean.

Frontiers in genetics·2022
Same author

Ability of <sup>68</sup> Ga-PSMA PET/CT SUVmax to differentiate ISUP GG2 from GG3 in intermediate-risk prostate cancer: A single-center retrospective study of 147 patients.

Cancer medicine·2022
Same author

Immunotherapy-Associated Hypophysitis under Anti-PD1: Two Case Reports.

Endocrine, metabolic & immune disorders drug targets·2022
Same author

Recommended practices and ethical considerations for natural language processing-assisted observational research: A scoping review.

Clinical and translational science·2022
Same author

HDACs/mTOR inhibitor synergizes with pyrotinib in HER2-positive pancreatic cancer through degradation of mutant P53.

Cancer cell international·2022

Related Experiment Video

Updated: Jul 8, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

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

Published on: June 13, 2025

DuoFlow-KG: a dual-modal evidence retrieval framework for high-density LLM-augmented KGQA.

Liwei Wang1, Zhijun Xie2, Rui Wang1

  • 1Faculty of Information Science and Engineering, Ningbo University, Ningbo, 315211, China.

Scientific Reports
|July 6, 2026
PubMed
Summary

DuoFlow-KG enhances knowledge graph question answering by unifying semantic and structural evidence retrieval. This framework improves multi-hop reasoning by creating dense subgraphs, leading to better accuracy in complex question answering tasks.

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

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

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Jul 8, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

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

Published on: June 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

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

Published on: December 6, 2024

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Knowledge Representation and Reasoning

Background:

  • Knowledge Graph Question Answering (KGQA) often uses a retrieval-reasoning approach.
  • Current retrieval methods struggle to balance semantic relevance and structural dependencies.
  • This leads to fragmented evidence and inefficient multi-hop reasoning.

Purpose of the Study:

  • To propose DuoFlow-KG, a unified dual-modal evidence retrieval framework for KGQA.
  • To improve the construction of compact, high-density evidence subgraphs.
  • To enhance multi-hop reasoning by integrating structure-semantic modeling.

Main Methods:

  • Developed a dual-directional knowledge anchoring strategy with inverse relation injection.
  • Introduced a dual-modal fusion module for unified embedding space projection.
  • Implemented a scalar diffusion mechanism for structural fingerprint generation.
  • Utilized a hierarchical weak-supervision scheme with diversity-aware sampling (Maximal Marginal Relevance).

Main Results:

  • DuoFlow-KG achieved state-of-the-art performance on WebQuestionsSP (77.28% F1) and ComplexWebQuestions (61.33% F1).
  • The framework successfully constructs compact, high-density evidence subgraphs.
  • Ablation studies confirmed the effectiveness of semantic modeling, structural reasoning, and bidirectional anchoring.

Conclusions:

  • DuoFlow-KG offers a unified approach to evidence retrieval in KGQA.
  • The integrated structure-semantic modeling significantly improves multi-hop reasoning capabilities.
  • The proposed methods are particularly effective for complex reasoning scenarios.