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

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.2K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.2K
Genetic Lingo01:11

Genetic Lingo

101.3K
Overview
101.3K
Higher Mental Functions of the Brain: Language01:10

Higher Mental Functions of the Brain: Language

751
Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
751
Improving Translational Accuracy02:07

Improving Translational Accuracy

2.5K
2.5K
Genomics02:02

Genomics

36.0K
Genomics is the science of genomes: it is the study of all the genetic material of an organism. In humans, the genome consists of information carried in 23 pairs of chromosomes in the nucleus, as well as mitochondrial DNA. In genomics, both coding and non-coding DNA is sequenced and analyzed. Genomics allows a better understanding of all living things, their evolution, and their diversity. It has a myriad of uses: for example, to build phylogenetic trees, to improve productivity and...
36.0K
lncRNA - Long Non-coding RNAs02:39

lncRNA - Long Non-coding RNAs

8.5K
In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA...
8.5K

You might also read

Related Articles

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

Sort by
Same author

Complement C5a/C5aR1 pathway facilitates glioblastoma progression via fostering glioma stem cell-macrophage symbiosis.

Journal of neuroinflammation·2026
Same author

Factors influencing delays in seeking medical care among elderly patients with pulmonary tuberculosis in Ningbo: a study conducted from 2015 to 2023.

Journal of health, population, and nutrition·2026
Same author

Advances in Biomaterial-Based Cardiac Organoids Engineering for Modeling Development and Congenital Heart Defects.

ACS applied bio materials·2026
Same author

Author Correction: Plasma membrane curvature regulates the formation of contacts with the endoplasmic reticulum.

Nature cell biology·2026
Same author

Cardiac-Derived ECM Microspheres for Enhanced hiPSC-CMs Maturation.

Advanced functional materials·2026
Same author

Non-equilibrium criticality-enhanced quantum sensing with superconducting qubits.

Science bulletin·2026
Same journal

MambaTab: A Plug-and-Play Model for Learning Tabular Data.

Proceedings. IEEE Conference on Multimedia Information Processing and Retrieval·2025
See all related articles

Related Experiment Video

Updated: Jun 8, 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

505

LitAI: Enhancing Multimodal Literature Understanding and Mining with Generative AI.

Gowtham Medisetti1, Zacchaeus Compson1, Heng Fan1

  • 1University of North Texas, Denton, TX, USA.

Proceedings. IEEE Conference on Multimedia Information Processing and Retrieval
|November 1, 2024
PubMed
Summary
This summary is machine-generated.

LitAI enhances scientific literature retrieval by using generative AI and optical character recognition (OCR) to extract text, tables, and figures from PDFs. This approach outperforms existing methods in biological and ecological sciences.

Keywords:
ChatGPTGPT-4Generative AILiterature MiningOCRPrompt Engineering

More Related Videos

Visualizing Lignification Dynamics in Plants with Click Chemistry: Dual Labeling is BLISS!
10:40

Visualizing Lignification Dynamics in Plants with Click Chemistry: Dual Labeling is BLISS!

Published on: January 26, 2018

11.9K
Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats
10:04

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Published on: May 9, 2018

11.3K

Related Experiment Videos

Last Updated: Jun 8, 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

505
Visualizing Lignification Dynamics in Plants with Click Chemistry: Dual Labeling is BLISS!
10:40

Visualizing Lignification Dynamics in Plants with Click Chemistry: Dual Labeling is BLISS!

Published on: January 26, 2018

11.9K
Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats
10:04

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Published on: May 9, 2018

11.3K

Area of Science:

  • Information retrieval
  • Scientific literature analysis
  • Artificial intelligence in research

Background:

  • Scientific research relies on effective information processing and retrieval from diverse literature formats.
  • Multimodal literature (text, tables, figures) poses challenges for traditional information retrieval systems.

Purpose of the Study:

  • To introduce LitAI, a novel approach for enhanced multimodal information retrieval from scientific literature.
  • To leverage generative AI and optical character recognition (OCR) for extracting information from PDF documents.

Main Methods:

  • Developed LitAI, integrating OCR with generative AI services for multimodal data extraction.
  • Utilized prompt engineering and in-context learning within generative AI for precise information extraction.
  • Evaluated LitAI on datasets from ecological and biological sciences.

Main Results:

  • LitAI demonstrated superior performance in retrieving text, tables, and figures compared to baselines.
  • Empirical evaluations showed significant improvements over Tesseract-OCR and GPT-4.
  • The approach effectively handles multimodal information within scientific PDFs.

Conclusions:

  • LitAI offers a powerful and accessible solution for multimodal information retrieval in scientific literature.
  • Generative AI, combined with OCR, significantly advances the capabilities of literature analysis tools.
  • The developed prompts and methodology provide a robust framework for future research in AI-driven scientific discovery.