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

2025/05/16 by Makoto Sato, Sato, Makoto
Neuroscience · Psychology · #Embodied and Extended Cognition #Mental Health via Writing #Action Observation and Synchronization

paper · pdf · doi:10.48550/arxiv.2505.10948

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.

Citations

• Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models
• Waking Up an AI: A Quantitative Framework for Prompt-Induced Phase Transition in Large Language Models
• Exploiting Language Models as a Source of Knowledge for Cognitive Agents
• An aperiodic monotile
• Locating and Editing Factual Associations in GPT
• What Does BERT Look At? An Analysis of BERT's Attention
• Are Sixteen Heads Really Better than One?
• Attention Is All You Need
• The magical number seven, plus or minus two: Some limits on our capacity for processing information.

Related

• Waking Up an AI: A Quantitative Framework for Prompt-Induced Phase Transition in Large Language Models
• Beyond "Hallucinations": A Framework for Stable Human-AI Reasoning
• Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models
• Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI
• Psychomatics -- A Multidisciplinary Framework for Understanding Artificial Minds