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

Modeling and Similitude01:12

Modeling and Similitude

252
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
252

You might also read

Related Articles

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

Sort by
Same author

VizDefender: Unmasking Visualization Tampering Through Proactive Localization and Intent Inference.

IEEE transactions on visualization and computer graphics·2026
Same author

VizQStudio: Iterative Visualization Literacy MCQs Design With Simulated Students.

IEEE transactions on visualization and computer graphics·2026
Same author

Follow the Signs or the Crowd? Effects of Environmental Load and Crowd Dynamics in VR Evacuation.

IEEE transactions on visualization and computer graphics·2026
Same author

SceneLoom: Communicating Data with Scene Context.

IEEE transactions on visualization and computer graphics·2025
Same author

CellScout: Visual Analytics for Mining Biomarkers in Cell State Discovery.

IEEE transactions on visualization and computer graphics·2025
Same author

TrajLens: Visual Analysis for Constructing Cell Developmental Trajectories in Cross-Sample Exploration.

IEEE transactions on visualization and computer graphics·2025

Related Experiment Video

Updated: Jun 13, 2025

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
07:36

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

15.7K

How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?

Leo Yu-Ho Lo, Huamin Qu

    IEEE Transactions on Visualization and Computer Graphics
    |September 12, 2024
    PubMed
    Summary

    Multimodal Large Language Models (LLMs) show strong potential for detecting misleading charts. This research highlights their ability to enhance data interpretation and combat misinformation effectively.

    Area of Science:

    • Data Visualization
    • Artificial Intelligence
    • Information Integrity

    Background:

    • Misleading charts distort data perception, leading to misinterpretations and poor decisions.
    • Automatic detection of misleading charts is crucial for maintaining information integrity.
    • Advancements in multimodal Large Language Models (LLMs) offer new possibilities for chart analysis.

    Purpose of the Study:

    • To explore the capabilities of multimodal LLMs in detecting misleading charts.
    • To assess the impact of various prompting strategies on LLM performance in chart analysis.
    • To develop scalable methods for identifying a wide range of chart issues using LLMs.

    Main Methods:

    • Utilized a dataset of misleading charts from prior research.
    • Employed nine distinct prompts, from simple to complex, to test four multimodal LLMs.

    More Related Videos

    Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
    09:27

    Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

    Published on: October 13, 2018

    9.9K
    Visualizing Visual Adaptation
    04:43

    Visualizing Visual Adaptation

    Published on: April 24, 2017

    8.9K

    Related Experiment Videos

    Last Updated: Jun 13, 2025

    Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
    07:36

    Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

    Published on: November 30, 2018

    15.7K
    Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
    09:27

    Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

    Published on: October 13, 2018

    9.9K
    Visualizing Visual Adaptation
    04:43

    Visualizing Visual Adaptation

    Published on: April 24, 2017

    8.9K
  • Conducted three experiments, progressively expanding detection from 5 to over 21 chart issues.

    • Main Results:

    • Multimodal LLMs demonstrated strong capabilities in chart comprehension and critical thinking.
    • Prompting strategies significantly influenced the models' accuracy in detecting chart issues.
    • Scalable methods were developed to address challenges in detecting a broad spectrum of misleading chart types.

    Conclusions:

    • Multimodal LLMs are effective tools for identifying misleading charts and enhancing visualization literacy.
    • There is significant potential to leverage LLMs in combating data misrepresentation and supporting critical thinking.
    • This study validates the application of LLMs in addressing the critical issue of misleading visualizations.