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

Retrieval01:12

Retrieval

387
Retrieval is the process of getting information out of memory storage and back into conscious awareness. This ability is essential for daily tasks like brushing hair and teeth, driving to work, and performing job duties. Retrieval occurs in three ways: recall, recognition, and relearning.
Recall involves accessing information without cues, such as during an essay test, where individuals must retrieve facts and concepts from memory unaided. Another example is remembering the name of a colleague...
387
Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

196
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
196

You might also read

Related Articles

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

Sort by
Same author

Memory strength at reactivation, not memory age, governs prediction error-driven updating of naturalistic event memory.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
Same author

Memory in the Palm of Your Hand: Smartphone-based Methods for Measuring Memory in the Wild.

Journal of cognitive neuroscience·2026
Same author

Improving autobiographical episodic memory, quality of life, and sense of self with a smartphone intervention in early dementia: A case study.

Neuropsychological rehabilitation·2026
Same author

The hippocampus becomes topographically and functionally specialized along the longitudinal axis with development.

Nature communications·2026
Same author

Natural language processing captures memory content associated with shared neural patterns at encoding and retrieval.

Communications psychology·2026
Same author

Independent Typers Exist: A Reply to Letters on Why We Need to Study Assisted Methods to Teach Typing.

Autism research : official journal of the International Society for Autism Research·2026

Related Experiment Video

Updated: Jan 8, 2026

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

986

Event segmentation applications in large language model enabled automated recall assessments.

Ryan A Panela1,2, Alexander J Barnett3,4, Morgan D Barense5,3

  • 1Rotman Research Institute, Baycrest Academy for Research and Education, North York, Toronto, ON, Canada. ryan.panela@utoronto.ca.

Communications Psychology
|December 15, 2025
PubMed
Summary

Large Language Models (LLMs) can now automate event segmentation and recall assessment in narratives. This AI approach offers a scalable and accurate alternative to subjective human evaluations for memory and perception research.

More Related Videos

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

2.0K
Examining Recall Memory in Infancy and Early Childhood Using the Elicited Imitation Paradigm
06:35

Examining Recall Memory in Infancy and Early Childhood Using the Elicited Imitation Paradigm

Published on: April 28, 2016

35.0K

Related Experiment Videos

Last Updated: Jan 8, 2026

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

986
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

2.0K
Examining Recall Memory in Infancy and Early Childhood Using the Elicited Imitation Paradigm
06:35

Examining Recall Memory in Infancy and Early Childhood Using the Elicited Imitation Paradigm

Published on: April 28, 2016

35.0K

Area of Science:

  • Cognitive Science
  • Artificial Intelligence
  • Neuroscience

Background:

  • Event segmentation is crucial for perception, encoding, and memory recall, influencing comprehension and experience.
  • Current methods for assessing event segmentation and recall rely on subjective, time-intensive human judgments.
  • Existing automated approaches lack sufficient validity and ease of implementation.

Purpose of the Study:

  • To leverage Large Language Models (LLMs) for automating event segmentation and recall assessment in written narratives.
  • To validate LLM-based methods against human annotations for accuracy and consistency.
  • To develop a scalable AI-driven framework for studying perception and memory.

Main Methods:

  • Utilized chat completion models for automated event segmentation from narratives.
  • Employed text-embedding models to assess the recall of segmented narrative events.
  • Validated LLM outputs against human segmentation patterns and recall performance.

Main Results:

  • LLMs accurately identified event boundaries in narratives, demonstrating high validity.
  • Human event segmentation showed greater consistency with LLM outputs than among human annotators.
  • Automated recall assessment using semantic similarity effectively estimated participant recall performance.

Conclusions:

  • LLMs provide a scalable and accurate alternative to manual scoring for event segmentation and recall.
  • This AI-driven methodology enhances the study of perception, memory, and cognitive impairment.
  • The findings open new avenues for AI-assisted cognitive research.