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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Language and Cognition01:27

Language and Cognition

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.
Components of Language01:24

Components of Language

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. “eh”). Phonemes combine to...
Language Development01:22

Language Development

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...
Language01:16

Language

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

Higher Mental Functions of the Brain: Language

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...

You might also read

Related Articles

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

Sort by
Same author

Philosophy of cognitive science in the age of deep learning.

Wiley interdisciplinary reviews. Cognitive science·2024
Same author

Neural correlates of the DMT experience assessed with multivariate EEG.

Scientific reports·2019
See all related articles

Related Experiment Video

Updated: Jul 2, 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

Keeping it real: Language models implement algorithms to solve linguistic tasks.

Raphaël Millière1

  • 1Faculty of Philosophy, University of Oxford, UK raphael.milliere@philosophy.ox.ac.uk.

The Behavioral and Brain Sciences
|June 30, 2026
PubMed
Summary

Language models (LMs) implement specific algorithms for linguistic tasks, not just discover patterns. Causal abstraction rigorously tests if these algorithms align with linguistic theory, supporting existing proposals.

Related Experiment Videos

Last Updated: Jul 2, 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

Area of Science:

  • Computational linguistics
  • Artificial intelligence
  • Cognitive science

Background:

  • The debate on whether language models (LMs) discover "real patterns" or implement specific algorithms for linguistic tasks.
  • The role of mechanistic interpretability in understanding LM decision-making processes.

Purpose of the Study:

  • To propose a framework for rigorously testing algorithmic convergence in LMs.
  • To investigate whether LMs implement algorithms consistent with linguistic theory.
  • To support a conciliatory proposal regarding LM capabilities.

Main Methods:

  • Utilizing the framework of causal abstraction.
  • Developing methods to rigorously test algorithmic implementations in LMs.
  • Comparing LM-derived algorithms with those posited by linguistic theory.

Main Results:

  • Demonstrating that mechanistic interpretability reveals LMs implement specific algorithms.
  • Providing a method to rigorously test LM algorithmic convergence.
  • Showing that LMs can converge on algorithms aligned with linguistic theory.

Conclusions:

  • The framing of LMs discovering "real patterns" underplays their algorithmic nature.
  • Mechanistic interpretability and causal abstraction offer rigorous tools for LM analysis.
  • LM research can benefit from a framework that bridges pattern discovery and algorithmic implementation.