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

TL;DR

This paper introduces a novel framework using Conceptual Blending Theory to analyze how large language models process and transition between meanings through prompts, revealing insights into their cognitive-like behaviors.

Contribution

It operationalizes Conceptual Blending Theory in LLMs, linking linguistics and neuroscience to explore prompt-induced cognitive transitions and hallucinations.

Findings

Identifies structural parallels between LLMs and biological cognition.

Reveals mechanisms of meaning blending and compression in LLMs.

Proposes prompt engineering as a scientific method for studying cognition.

Abstract

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.