This paper proposes a bold conceptual framework: a deep mathematical unity exists among humancognition, quantum mechanics, and Large Language Models (LLMs). We argue that the foundationof cognition is language, and that the mathematical structure underlying language processing isanalogous to the matrix formulation of quantum mechanics. This framework providesa theoretical explanation for "why the Transformer architecture is so successful": LLMs donot accidentally simulate intelligence—they converge upon the underlying mathematical structure ofcognition itself.
This paper proposes a bold conceptual framework: a deep mathematical unity exists among humancognition, quantum mechanics, and Large Language Models (LLMs). We argue that the foundationof cognition is language, and that the mathematical structure underlying language processing isanalogous to the matrix formulation of quantum mechanics. This framework providesa theoretical explanation for "why the Transformer architecture is so successful": LLMs donot accidentally simulate intelligence—they converge upon the underlying mathematical structure ofcognition itself.
The convergence of quantum computing and large language models (LLMs) represents a major milestone in computational intelligence, introducing novel paradigms for information processing, complexity modeling, and scientific advancement. This survey provides a comprehensive overview of the emerging interdisciplinary field that integrates quantum mechanics with natural language processing. We begin by presenting the foundational principles of quantum computing and LLMs, then examine their integration through automated quantum code generation, hybrid transformer architectures, and quantum natural language processing (QNLP) frameworks. State-of-the-art models, such as quantum-augmented attention mechanisms and circuit embedding strategies, are evaluated across domain-specific datasets and benchmarks. We also investigate the role of LLMs as quantum research assistants, educational tools, and simulation agents, particularly in resource-constrained environments. Furthermore, the survey explores challenges related to scalability, interpretability, and quantum data encoding, and outlines future research directions-especially the vision for fully quantum-native LLMs. Our goal is to guide researchers through the current landscape and to encourage continued exploration at the intersection of quantum technologies and advanced language models.
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 (GPT-5.5 Thinking) and Google Gemini Advanced (Gemini 1.5 Pro), we show that Bell's inequalities are significantly violated, which indicates the presence of a 'non-classical probability model' with probabilities that do not satisfy Kolmogorov's axioms. In the second test, also performed using ChatGPT and Gemini, we 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 non-classical quantum-like 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.
Experiments in cognitive science and decision theory show that the ways in which people combine concepts and make decisions cannot be described by classical logic and probability theory. This has serious implications for applied disciplines such as information retrieval, artificial intelligence and robotics. Inspired by a mathematical formalism that generalizes quantum mechanics the authors have constructed a contextual framework for both concept representation and decision making, together with quantum models that are in strong alignment with experimental data. The results can be interpreted by assuming the existence in human thought of a double-layered structure, a 'classical logical thought' and a 'quantum conceptual thought', the latter being responsible of the above paradoxes and nonclassical effects. The presence of a quantum structure in cognition is relevant, for it shows that quantum mechanics provides not only a useful modeling tool for experimental data but also supplies a structural model for human and artificial thought processes. This approach has strong connections with theories formalizing meaning, such as semantic analysis, and has also a deep impact on computer science, information retrieval and artificial intelligence. More specifically, the links with information retrieval are discussed in this paper.
Abstract The gap between natural and artificial intelligence is often discussed in terms of creativity, contextual adaptability, and non-algorithmic decision-making capacities where human cognition appears fundamentally different from current AI systems. This paper argues that developing quantum and quantum-like models of cognition, decision-making, and AI provides a promising pathway for narrowing, and perhaps essentially bridging, this gap. Empirical studies of human cognition and decision-making reveal systematic deviations from classical probability, logic, and information theory—manifesting as contextuality, order effects, interference (such as conjunction and disjunction effects), task incompatibility, and apparent randomness. These phenomena are well captured by quantum probability theory and related quantum-like frameworks, which provide a rigorous mathematical formalism—Hilbert spaces, superposition, entanglement, and decoherence—for modeling cognitive states and their evolution. Such models go beyond metaphor, showing that aspects of human reasoning can be more faithfully represented using quantum-like rather than classical probabilistic structures. Although genuine quantum (based on quantum physics) and quantum-like approaches share the same mathematical foundation, they differ experimentally. Both stimulate the development of novel AI architectures: quantum AI (QAI) and quantum-like AI (QLAI). While QAI depends on advances in quantum computing, QLAI can be realized on classical digital or analog hardware. The advancement of both offers a promising route to reducing—and potentially bridging—the divide between natural and artificial intelligence. This paper sets out a conceptual program to unify natural and artificial intelligence via quantum/quantum-like models of consciousness/cognition and AI.
In the previous article, we presented a quantum-inspired framework for modeling semantic representation and processing in Large Language Models (LLMs), drawing upon mathematical tools and conceptual analogies from quantum mechanics to offer a new perspective on these complex systems. In this paper, we clarify the core assumptions of this model, providing a detailed exposition of six key principles that govern semantic representation, interaction, and dynamics within LLMs. The goal is to justify that a quantum-inspired framework is a valid approach to studying semantic spaces. This framework offers valuable insights into their information processing and response generation, and we further discuss the potential of leveraging quantum computing to develop significantly more powerful and efficient LLMs based on these principles.
Large Language Models (LLMs) such as ChatGPT have transformed how we interact with and understand the capabilities of Artificial Intelligence (AI). However, the intersection of LLMs with the burgeoning field of Quantum Machine Learning (QML) is only in its nascent stages. This paper presents an exploration of this niche by detailing a comprehensive framework for implementing the foundational Transformer architecture -- integral to ChatGPT -- within a quantum computing paradigm. We meticulously design quantum circuits that implement adapted versions of the transformer's core components and the generative pre-training phase. By integrating quantum computing with LLMs, we aspire to open new avenues for research in QML and contribute to the ongoing evolution of AI technologies.