Identifying Quantum Structure in AI Language: Evidence for Evolutionary Convergence of Human and Artificial Cognition

2025-11-21

AI Summary

This study investigates whether human cognition and large language models (LLMs) share quantum-structural features in conceptual combination and semantic processing. Method: We conducted cognitive experiments assessing the extent to which ChatGPT and Gemini violate Bell inequalities in semantic judgment tasks, and analyzed their lexical frequency distributions for statistical signatures—specifically, Bose–Einstein versus Maxwell–Boltzmann statistics. Contribution/Results: Both LLMs exhibit statistically significant violations of Bell inequalities and display lexical frequency distributions consistent with Bose–Einstein statistics—aligning closely with empirical patterns observed in human semantic behavior and large-scale corpora. These findings support the “systematic emergence of quantum structure in the concept–language domain” hypothesis, establishing the first unified framework explaining convergent evolutionary trajectories in human and artificial semantic organization. The results challenge classical-probabilistic and distributed-representation paradigms underlying traditional neural network models.

Technology Category

Machine Learning: Quantum Machine LearningNatural Language Processing: (Large) Language ModelsCognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systemsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

We present the results of cognitive tests on conceptual combinations, performed using specific Large Language Models (LLMs) as test subjects. In the first test, performed with ChatGPT and Gemini, we show that Bell's inequalities are significantly violated, which indicates the presence of 'quantum entanglement' in the tested concepts. In the second test, also performed using ChatGPT and Gemini, we instead identify the presence of 'Bose-Einstein statistics', rather than the intuitively expected 'Maxwell-Boltzmann statistics', in the distribution of the words contained in large-size texts. Interestingly, these findings mirror the results previously obtained in both cognitive tests with human participants and information retrieval tests on large corpora. Taken together, they point to the 'systematic emergence of quantum structures in conceptual-linguistic domains', regardless of whether the cognitive agent is human or artificial. Although LLMs are classified as neural networks for historical reasons, we believe that a more essential form of knowledge organization takes place in the distributive semantic structure of vector spaces built on top of the neural network. It is this meaning-bearing structure that lends itself to a phenomenon of evolutionary convergence between human cognition and language, slowly established through biological evolution, and LLM cognition and language, emerging much more rapidly as a result of self-learning and training. We analyze various aspects and examples that contain evidence supporting the above hypothesis. We also advance a unifying framework that explains the pervasive quantum organization of meaning that we identify.

Problem

• Detects quantum entanglement in AI language models
• Identifies Bose-Einstein statistics in word distributions
• Explains evolutionary convergence in human and AI cognition

Innovation

• LLMs demonstrate quantum entanglement in conceptual combinations
• LLMs exhibit Bose-Einstein statistics in word distributions
• Quantum structures emerge in both human and AI cognition