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

Classification of Systems-I01:26

Classification of Systems-I

725
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
725
Aggregates Classification01:29

Aggregates Classification

988
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
988
Classification of Systems-II01:31

Classification of Systems-II

638
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
638
Confidence Coefficient01:24

Confidence Coefficient

9.1K
The confidence coefficient is also known as the confidence level or degree of confidence. It is the percent expression for the probability, 1-α, that the confidence interval contains the true population parameter assuming that the confidence interval is obtained after sufficient unbiased sampling; for example, if the CL = 90%, then in 90 out of 100 samples the interval estimate will enclose the true population parameter. Here α is the area under the curve, distributed equally under...
9.1K
Force Classification01:22

Force Classification

2.8K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.8K

You might also read

Related Articles

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

Sort by
Same author

Multimodal Deep Learning with Routine Clinical Data for Recurrence Risk Stratification in HR<sup>+</sup>/HER2<sup>-</sup> Early Breast Cancer.

Research (Washington, D.C.)·2026
Same author

10 years trends and hospitalization outcomes of non-neonatal tetanus: a large-scale multicenter retrospective study in China.

Critical care (London, England)·2026
Same author

Triptolide alleviates hyperosmotic stress-induced human corneal epithelial cell damage by inhibiting NLRP3 inflammasome-mediated pyroptosis via the TLR4/NF-κB pathway.

Frontiers in medicine·2026
Same author

Complex associations of adverse childhood and adulthood experiences with incident depressive symptoms in middle-aged and older Chinese adults.

BMC psychology·2026
Same author

An Advanced Robust van der Waals Heterostructure Photodetector with Ultralow Dark Current and a Large Linear Dynamic Range for Polarization Imaging and Optical Communication.

ACS applied materials & interfaces·2026
Same author

The regulatory mechanism of circadian clock gene Cry on estrogen secretion in Bactrian camels.

Biology of reproduction·2026

Related Experiment Video

Updated: Apr 23, 2026

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

1.3K

Large language model-based paper classification framework with key-insight extraction and confidence-weighted voting.

Zihan Song1, Shan Huang1, Ngeemasara Thapa2

  • 1College of Industrial Internet, Hubei Engineering Institute, China.

Research Synthesis Methods
|April 22, 2026
PubMed
Summary
This summary is machine-generated.

Large language models (LLMs) can now classify research articles for systematic reviews (SRs) with high accuracy. A new framework using key-insight extraction and confidence-weighted voting significantly improves efficiency and reliability in evidence synthesis.

Keywords:
artificial intelligenceevidence synthesislarge language modelliterature screeningpaper classificationsystematic review

Related Experiment Videos

Last Updated: Apr 23, 2026

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

1.3K

Area of Science:

  • Bibliometrics
  • Artificial Intelligence
  • Information Science

Background:

  • Systematic reviews (SRs) are essential for evidence-based research but are resource-intensive.
  • The growing volume of publications strains current screening and classification methods.
  • Large language models (LLMs) offer potential for automating literature classification in SRs.

Purpose of the Study:

  • To evaluate LLM performance in large-scale, multi-class literature classification for SRs.
  • To develop and assess an LLM-based framework for enhanced literature classification.
  • To improve the efficiency and reliability of evidence synthesis.

Main Methods:

  • Developed an LLM framework utilizing full-text key-insight extraction for literature classification.
  • Created a manually curated dataset of 900 articles from 17 SRs for evaluation.
  • Implemented a confidence-weighted voting (CWV) mechanism with multiple LLMs.

Main Results:

  • Key-insight-based classification (KBC) outperformed abstract-based classification (ABC).
  • The CWV method achieved the highest macro F1-score of 0.796.
  • LLM classification performance was comparable to human reviewers, exceeding K-means clustering (0.446).

Conclusions:

  • LLM-based frameworks show significant potential for supporting large-scale SRs.
  • Key-insight extraction and CWV enhance classification accuracy and robustness.
  • Zero-shot LLMs offer adaptability across domains without fine-tuning, improving evidence synthesis.