用提示工程揭示大模型如何融合意义，探索人工智能与人类认知的共性。
The Way We Prompt: Conceptual Blending, Neural Dynamics, and Prompt-Induced Transitions in LLMs
- 基于概念融合理论设计提示实验，研究大模型的意义整合机制。
- 发现提示引发的思维跃迁与幻觉现象，揭示人工与生物认知的异同。
- 提示工程不仅是技术手段，更是探测语义深层结构的科学方法。
大型语言模型（LLMs）受神经科学启发，常表现出类似人格与智能的行为，但其内在机制仍不清晰。本文将概念融合理论（CBT）转化为实验框架，通过提示驱动的方法揭示大模型如何融合与压缩意义。系统研究提示诱导的跃迁（PIT）与提示诱导的幻觉（PIH），发现人工与生物认知在结构上存在相似与差异。该方法融合语言学、神经科学与实证人工智能研究，表明人机协作可成为未来认知科学的活体原型。本工作提出，提示工程不仅是技术工具，更是探测意义深层结构的科学方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。