The Way We Prompt: Conceptual Blending, Neural Dynamics, and Prompt-Induced Transitions in LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Sato, Makoto
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912379484241920
author Sato, Makoto
author_facet Sato, Makoto
contents Large language models (LLMs), inspired by neuroscience, exhibit behaviors that often evoke a sense of personality and intelligence-yet the mechanisms behind these effects remain elusive. Here, we operationalize Conceptual Blending Theory (CBT) as an experimental framework, using prompt-based methods to reveal how LLMs blend and compress meaning. By systematically investigating Prompt-Induced Transitions (PIT) and Prompt-Induced Hallucinations (PIH), we uncover structural parallels and divergences between artificial and biological cognition. Our approach bridges linguistics, neuroscience, and empirical AI research, demonstrating that human-AI collaboration can serve as a living prototype for the future of cognitive science. This work proposes prompt engineering not just as a technical tool, but as a scientific method for probing the deep structure of meaning itself.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Way We Prompt: Conceptual Blending, Neural Dynamics, and Prompt-Induced Transitions in LLMs
Sato, Makoto
Computation and Language
Neurons and Cognition
Large language models (LLMs), inspired by neuroscience, exhibit behaviors that often evoke a sense of personality and intelligence-yet the mechanisms behind these effects remain elusive. Here, we operationalize Conceptual Blending Theory (CBT) as an experimental framework, using prompt-based methods to reveal how LLMs blend and compress meaning. By systematically investigating Prompt-Induced Transitions (PIT) and Prompt-Induced Hallucinations (PIH), we uncover structural parallels and divergences between artificial and biological cognition. Our approach bridges linguistics, neuroscience, and empirical AI research, demonstrating that human-AI collaboration can serve as a living prototype for the future of cognitive science. This work proposes prompt engineering not just as a technical tool, but as a scientific method for probing the deep structure of meaning itself.
title The Way We Prompt: Conceptual Blending, Neural Dynamics, and Prompt-Induced Transitions in LLMs
topic Computation and Language
Neurons and Cognition
url https://arxiv.org/abs/2505.10948