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

Hypothesis: Accept or Fail to Reject?01:17

Hypothesis: Accept or Fail to Reject?

27.3K
The outcome of any hypothesis testing leads to rejecting or not rejecting the null hypothesis. This decision is taken based on the analysis of the data, an appropriate test statistic, an appropriate confidence level, the critical values, and P-values. However, when the evidence suggests that the null hypothesis cannot be rejected, is it right to say, 'Accept' the null hypothesis?
There are two ways to indicate that the null hypothesis is not rejected. 'Accept' the null...
27.3K
Language and Cognition01:27

Language and Cognition

291
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
291
Higher Mental Functions of the Brain: Language01:10

Higher Mental Functions of the Brain: Language

618
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...
618
Limits to Natural Selection01:38

Limits to Natural Selection

30.8K
Organisms that are well-adapted to their environment are more likely to survive and reproduce. However, natural selection does not lead to perfectly adapted organisms. Several factors constrain natural selection.
30.8K
Accuracy, limits, and approximation01:28

Accuracy, limits, and approximation

409
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
409
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

335
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
335

You might also read

Related Articles

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

Sort by
Same author

Using LLMs to Infer Non-Binary COVID-19 Sentiments of Chinese Microbloggers.

Entropy (Basel, Switzerland)·2025
Same author

Diffusive persistence on disordered lattices and random networks.

Physical review. E·2024
Same author

Protect our environment from information overload.

Nature human behaviour·2024
Same author

A network generator for covert network structures.

Information sciences·2023
Same author

Dynamics of crime activities in the network of city community areas.

Applied network science·2023
Same author

Robust, scalable, and informative clustering for diverse biological networks.

Genome biology·2023

Related Experiment Video

Updated: May 10, 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

462

Testing the limits of large language models in debating humans.

James Flamino1, Mohammed Shahid Modi1, Boleslaw K Szymanski2

  • 1Department of Computer Science and Network Science and Technology Center, Rensselaer Polytechnic Institute, Troy, NY, USA.

Scientific Reports
|April 22, 2025
PubMed
Summary

Large Language Models (LLMs) show promise in human communication and sociological experiments. While agents debate effectively, humans perceive them as less convincing, revealing distinct behavioral patterns.

Keywords:
Artificial intelligenceHuman–computer interactionLarge language modelsOpinion consensusSocial dynamicsStatistical analysis

More Related Videos

One Dimensional Turing-Like Handshake Test for Motor Intelligence
14:05

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

26.7K
The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition
05:15

The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

Published on: February 19, 2018

10.7K

Related Experiment Videos

Last Updated: May 10, 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

462
One Dimensional Turing-Like Handshake Test for Motor Intelligence
14:05

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

26.7K
The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition
05:15

The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

Published on: February 19, 2018

10.7K

Area of Science:

  • Artificial Intelligence
  • Sociology
  • Human-Computer Interaction

Background:

  • Large Language Models (LLMs) demonstrate advanced human-like communication capabilities.
  • The integration of LLM-powered agents in sociological research presents novel opportunities and challenges.
  • Assessing the viability of LLM agents as participants in conversational experiments is crucial.

Purpose of the Study:

  • To rigorously evaluate the performance and perception of LLM-powered agents in debate-based opinion consensus games.
  • To compare the conversational and debating behaviors of human participants and LLM agents.
  • To determine the impact of LLM agents on overall group productivity and consensus formation.

Main Methods:

  • A preregistered study involving multiple debate-based opinion consensus games.
  • Experimental conditions included all-human groups, all-agent groups, and mixed human-agent groups.
  • Collection and analysis of behavioral metrics for both human and agent participants.

Main Results:

  • LLM agents demonstrated superior focus on debate topics compared to human participants, enhancing overall productivity.
  • Humans perceived LLM agents as less convincing and confident than human debaters.
  • Measurable deviations were observed in behavioral metrics between human and agent participants.
  • Agent debater behavior generated distinct patterns compared to human-generated data.

Conclusions:

  • LLM agents are capable debaters and can improve experimental productivity.
  • Despite their effectiveness, agents are perceived differently by humans, highlighting a gap in social cues and confidence.
  • Distinct behavioral patterns suggest that current LLM agents do not fully replicate human interaction dynamics in debates.