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

Lateralization

Lateralization

Brain lateralization refers to the division of mental processes and functions between the two hemispheres of the brain, a phenomenon that optimizes neural efficiency and underpins complex abilities in humans. This specialization allows each hemisphere to perform tasks where it has a comparative advantage, facilitating more refined cognitive capabilities across different domains.

Self-Report Tests of Personality

Self-Report Tests of Personality

Self-report inventories are objective personality assessments that use multiple-choice items or numbered scales, typically ranging from 1 (strongly disagree) to 5 (strongly agree). They are often called Likert scales after Rensis Likert. These inventories are widely used due to their ease of administration and cost-effectiveness. One of the most prominent examples is the Minnesota Multiphasic Personality Inventory (MMPI), initially developed in the 1940s to assess abnormal personality traits.

You might also read

Related Articles

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

Sort by

Same author

Snhg18 promotes hypoxic pulmonary hypertension by enhancing glycolysis.

Respiratory research·2026

Same author

The L-Ascorbic Acid Increases Proliferation and Differentiation of Yanbian Cattle Skeletal Muscle Satellite Cells by Activating the Akt/mTOR/P70S6K Signaling Pathway.

Food science of animal resources·2026

Same author

A green and clean phycocyanin-reinforced sodium alginate-based composite hydrogel sphere for selective and effective capture of Pb<sup>2+</sup> in seaweed juice concentrates.

International journal of biological macromolecules·2026

Same author

Development of scale-up isochoric freezing equipment for better preserving litchi fruit: Basic characteristics, aroma quality, and water status.

Food chemistry·2025

Same author

Large Language Model-Powered Protected Interface Evasion: Automated Discovery of Broken Access Control Vulnerabilities in Internet of Things Devices.

Sensors (Basel, Switzerland)·2025

Same author

Abnormal Functional Connectivity of the Primary Sensory Network in Autism Spectrum Disorder: Sex Differences, Early Overdevelopment, and Clinical Significance.

Brain and behavior·2025

Search research articles

Related Experiment Video

Updated: Mar 11, 2026

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

AIPsychoBench: Understanding the Psychometric Differences Between LLMs and Humans.

Wei Xie¹, Zhenhua Wang¹, Shuoyoucheng Ma¹

¹College of Computer Science and Technology, National University of Defense Technology.

Topics in Cognitive Science

|March 9, 2026

Summary

This summary is machine-generated.

AIPsychoBench is a new benchmark for assessing Large Language Models' (LLMs) psychological properties. It improves response rates and reduces bias, offering insights into linguistic impacts on LLM psychometrics.

Keywords:

Benchmark LLM Psychometrics

More Related 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

One Dimensional Turing-Like Handshake Test for Motor Intelligence

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

Related Experiment Videos

Last Updated: Mar 11, 2026

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

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

One Dimensional Turing-Like Handshake Test for Motor Intelligence

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

Area of Science:

Artificial Intelligence
Computational Psychology
Natural Language Processing

Background:

Large Language Models (LLMs) demonstrate human-like intelligence but suffer from uninterpretability, raising reliability concerns.
Existing psychometric assessments for LLMs fail due to fundamental differences between LLMs and humans, leading to high rejection rates.
Current methods do not account for linguistic variations, limiting the assessment of LLM psychological properties across different languages.

Purpose of the Study:

Introduce AIPsychoBench, a specialized benchmark designed to accurately assess the psychological properties of LLMs.
Enhance the interpretability and reliability of LLM evaluations by addressing limitations of human-centric psychological scales.
Investigate the impact of linguistic diversity on LLM psychometrics.

Main Methods:

Developed a lightweight role-playing prompt to bypass LLM alignment, improving effective response rates.
Compared the bias levels of the new prompt method against traditional jailbreak prompts.
Evaluated 112 psychometric subcategories across seven languages to measure score deviations relative to English.

Main Results:

The role-playing prompt significantly improved the average effective response rate from 70.12% to 90.40%.
The new method achieved substantially lower average biases (3.3% positive, 2.1% negative) compared to jailbreak prompts (9.8% positive, 6.9% negative).
Score deviations across seven languages ranged from 5% to 20.2% in 43 subcategories, indicating significant linguistic impact on LLM psychometrics.

Conclusions:

AIPsychoBench provides a more reliable and effective method for evaluating LLM psychological properties.
The benchmark demonstrates reduced bias and higher response rates, enhancing LLM interpretability.
This study offers the first comprehensive evidence of linguistic variations influencing LLM psychometric assessments.