Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Language Development01:22

Language Development

444
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
444
Language and Cognition01:27

Language and Cognition

438
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.
438
Language01:16

Language

422
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
422
Components of Language01:24

Components of Language

388
Language, whether spoken, signed, or written, consists of specific components: lexicon and grammar. The lexicon is the vocabulary of a language, comprising its words. Grammar is the set of rules used to convey meaning through the lexicon. For example, English grammar adds “-ed” to most verbs to indicate past tense. Words are formed by combining phonemes, which are the basic sound units of a language. Different languages have different sets of phonemes (e.g., “ah” vs.
388
Modeling and Similitude01:12

Modeling and Similitude

328
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...
328
Higher Mental Functions of the Brain: Language01:10

Higher Mental Functions of the Brain: Language

1.0K
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...
1.0K

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Will the widespread use of large language models in scientific writing undermine scientists' critical thinking?

PLoS biology·2026
Same author

Language-Invariant Strategies of Navigating Transitions in Joint Activities: Forms and Functions of Coordination Markers.

Cognitive science·2025
Same author

From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehave.

International journal of computer vision·2025
Same author

Conversational remembering.

Current opinion in psychology·2025
Same author

A Social Media Study of Portrayals of Bipolar Disorders on YouTube: Content and Thematic Analyses.

Journal of medical Internet research·2025
Same author

Potential evidence of reengagement attempts following interruptions of a triadic social game in bonobos and chimpanzees.

PloS one·2025
Same journal

Pronoun Resolution in Turkish: The Interplay of Referential Form, Word Order, and Implicit Causality.

Cognitive science·2026
Same journal

What's in a Color?: Language, Synesthesia, and Categorical Perception.

Cognitive science·2026
Same journal

Reasoning Beyond Explicit Rules: Adults' and Children's Use of Closure Principles in Novel Cases.

Cognitive science·2026
Same journal

Intermediary Object States Are Activated by Sentences Describing Completed Events.

Cognitive science·2026
Same journal

Large Language Models Estimate Fine-Grained Human Color-Concept Associations.

Cognitive science·2026
Same journal

Computational Models of Causal Reasoning: Bayesian Accounts of Normative Violations.

Cognitive science·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Sep 9, 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

681

¿Pueden los grandes modelos lingüísticos simular conversaciones humanas habladas?

Eric Mayor1, Lucas M Bietti2, Adrian Bangerter3

  • 1Department of Psychology, University of Basel.

Cognitive science
|September 1, 2025
PubMed
Resumen
Este resumen es generado por máquina.

Los grandes modelos de lenguaje (LLM) muestran una alineación exagerada y un uso inadecuado de marcadores conversacionales en comparación con las conversaciones telefónicas humanas. Los LLM actuales no simulan consistentemente el diálogo humano hablado de manera efectiva.

Palabras clave:
Métodos computacionalesCoordinación de las conversacionesLLM a la conversación LLMAlineamiento lingüísticoConversación hablada

Más Videos Relacionados

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

570
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K

Videos de Experimentos Relacionados

Last Updated: Sep 9, 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

681
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

570
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K

Área de la Ciencia:

  • Lingüística computacional
  • Inteligencia artificial
  • Interacción hombre-ordenador

Sus antecedentes:

  • Los grandes modelos de lenguaje (LLM) demuestran capacidades avanzadas para emular la cognición humana, particularmente en las interacciones basadas en el chat.
  • La capacidad de los LLM para simular la conversación humana hablada sigue siendo en gran medida inexplorada, a pesar de su potencial como un cambio de paradigma.

Objetivo del estudio:

  • Investigar hasta qué punto los grandes modelos de lenguaje (LLM) pueden simular con precisión la conversación humana hablada.
  • Comparar las características lingüísticas de las conversaciones generadas por LLM con las conversaciones telefónicas humanas.

Principales métodos:

  • Estudio 1: Comparación de las transcripciones del cuadro (SB) (conversaciones telefónicas humanas) con las transcripciones generadas por LLMs (GPT-4, Claude Sonnet 3.5, Vicuna, Wayfarer) utilizando indicaciones personalizadas.
  • El análisis se centró en la alineación (conceptual, sintáctica, léxica), los marcadores de coordinación y las aberturas y cierres conversacionales.
  • Estudio 2: Evaluación de la capacidad humana para distinguir las transcripciones generadas por LLM de las transcripciones SB humanas.

Principales resultados:

  • Las conversaciones de LLM exhibieron una alineación exagerada, aumentando a medida que avanzaba la conversación, a diferencia de las conversaciones humanas.
  • Los LLM demostraron un uso diferente y a menudo inadecuado de los marcadores de coordinación y aberturas y cierres de conversación diferentes.
  • Los evaluadores humanos pudieron distinguir las transcripciones generadas por LLM de las conversaciones humanas, lo que indica que los LLM no pasaron consistentemente por el diálogo humano.

Conclusiones:

  • Las conversaciones habladas generadas por los LLM actuales son cualitativa y cuantitativamente diferentes de las conversaciones humanas.
  • Las diferencias pueden derivarse de distinciones inherentes entre el diálogo hablado y el chat, o limitaciones en la capacitación y las capacidades de LLM.
  • Los avances futuros en los LLM y los datos de formación pueden mejorar la simulación, pero pueden persistir diferencias fundamentales.