Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Machine Learning and Knowledge Extraction

What ChatGPT Has to Say About Its Topological Structure: The Anyon Hypothesis

Michel R. P. Planat, Marcelo M. Amaral

Published Dec 15, 2024• 5 citations
Publisher

Abstract

Large language models (LLMs) achieve remarkable predictive capabilities but remain opaque in their internal reasoning, creating a pressing need for more interpretable artificial intelligence. Here, we propose bridging this explanatory gap by drawing on concepts from topological quantum computing (TQC), specifically the anyonic frameworks arising from SU(2)k theories. Anyons interpolate between fermions and bosons, offering a mathematical language that may illuminate the latent structure and decision-making processes within LLMs. By examining how these topological constructs relate to token interactions and contextual dependencies in neural architectures, we aim to provide a fresh perspective on how meaning and coherence emerge. After eliciting insights from ChatGPT and exploring low-level cases of SU(2)k models, we argue that the machinery of modular tensor categories and topological phases could inform more transparent, stable, and robust AI systems. This interdisciplinary approach suggests that quantum-theoretic principles may underpin a novel understanding of explainable AI.

DOI
10.3390/make6040137

Related papers

AI-Enhanced Simulation of Superalgebra-Based Topological Quantum Computation

Murali Krishna Pasupuleti

This paper presents a novel framework that integrates artificial intelligence with superalgebraic structures to simulate topological quantum computation (TQC) in systems governed by Lie superalgebras such as osp(1∣2) and sl(2∣1). By combining symbolic algebra, modular tensor category theory, and generative AI models—including variational autoencoders and diffusion models—the proposed system enables accurate, scalable simulation of non-Abelian anyonic braiding and fusion operations within graded symmetry constraints. The framework encodes superalgebraic invariants and topological rules into neural architectures, allowing physically valid and symmetry-preserving generation of braid paths and fusion outcomes. Experimental results demonstrate high fidelity, topological consistency, and robustness against noise, with successful emulation on quantum hardware platforms such as IBM Q and IonQ. This research opens new avenues for fault-tolerant, algebraically informed quantum simulation, circuit synthesis, and adaptive control in next-generation quantum technologies. Keywords: topological quantum computation, superalgebra, Lie superalgebras, modular tensor categories, osp(1∣2), sl(2∣1), anyons, braiding, fusion rules, symbolic AI, generative models, quantum simulation, quantum invariants, diffusion models, fault-tolerant quantum computing

International Journal of Academic and Industrial Research Innovations(IJAIRI)•Apr 11, 2025•0 citations

Quantum Computing for Explainable AI: Developing Quantum-inspired Interpretable Models for Complex Decision-making Systems

Chidera Onyeka Agu

The rapid advancement of Artificial Intelligence (AI) has heightened concerns about the opacity of decision-making processes in complex models, particularly deep neural networks. This research explores a novel paradigm that integrates quantum computing principles into Explainable AI (XAI) to enhance interpretability without compromising predictive accuracy. The study introduces a Quantum-inspired Interpretable Model (QIIM) framework that leverages Hilbert space embeddings, unitary transformations, and operator-based learning to represent knowledge in a mathematically transparent form. The proposed model computes interpretability through the expectation values of observable operators, enabling the decomposition of decisions into quantifiable, human-understandable components. To capture hierarchical relationships, a Tensor Network Interpretable Model (TNIM) is further developed, offering scalable insights into complex dependencies among features. Experimental evaluations—performed on benchmark datasets for decision-making tasks—demonstrate that the quantum-inspired models achieve competitive accuracy while significantly improving local and global interpretability metrics compared to classical XAI techniques. The findings underscore the potential of quantum formalism as a new foundation for transparent AI systems, bridging the gap between computational efficiency and explainability. This study contributes to both theoretical understanding and practical advancement in interpretable machine learning, paving the way for ethically aligned, transparent, and human-trustworthy AI-driven decision support systems.

British Journal of Computer Networking and Information Technology•Dec 3, 2025•1 citation

GPT on a Quantum Computer

Yidong Liao, Christopher Ferrie

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.

arXiv:2403.09418•Mar 14, 2024•24 citations

Representing modular tensor categories: a computer algebra system for topological quantum computing

D Roberts

Topological quantum computation (TQC) is a new fault-tolerant approach to quantum information, where computations are carried out by braiding particles called anyons. Anyons are quasiparticles that exist in 2 + 1 dimensions and are neither bosons or fermions. Modular tensor categories capture the structure of anyon systems and thus serve as models for topological quantum computation. However, program of using category theory to find higher-level structures and protocols has yet to be applied to TQC due to the difficulty of working with modular tensor categories. This difficulty could be greatly mitigated by the development of a computer algebra system to represent such categories. Thus, a computer algebra system for representing modular tensor categories within the symmetric monoidal 2-category 2Vect was developed. A general representation for 2Vect is described. This involves extending basic linear algebra operations to handle matrices of zero-dimension and 2-matrices (matrices of matrices). Then, representations for the 0-cells, 1-cells, and 2-cells of 2Vect are found. Due to the chosen representation, various structural isomorphisms are required to ensure equations expected of 1-categories hold in the 2-categories setting. These structural isomorphisms are explicitly constructed. In order to identify special categories, such as modular tensor categories, a diagrammatic language of monoidal categories is extended for 2-categories. This language is used to construct the axioms for these special categories within 2Vect. Finally, a way of implementing these axioms within 2Vect in the computer algebra system is described. This system will now be used for the investigation of higher-level structures within modular tensor categories to better understand the structure of topological quantum computing.

•Jan 1, 2011•0 citations

Algorithmic Transparency and Explainable AI using Quantum Information Theory

Jincheng Zhang

The increasing deployment of Artificial Intelligence (AI) systems across various domains necessitates a deeper understanding of their decision-making processes. Current explainable AI (XAI) techniques often struggle to provide truly transparent and reliable explanations, particularly for complex models like deep neural networks. This paper proposes a novel approach to algorithmic transparency and XAI leveraging concepts from quantum information theory. Specifically, we explore the potential of quantum entanglement and mutual information to represent and analyze AI model decisions in a fundamentally different way. Our framework represents model outputs as quantum states and investigates the correlations between these states and the input data. This analysis aims to identify the key factors driving the model's decision and provide a more intuitive and understandable explanation. We demonstrate that utilizing quantum information theory can offer a richer and more robust approach to XAI than traditional methods, potentially addressing limitations related to interpretability and trust in AI systems. This work lays the groundwork for a new paradigm in AI transparency, utilizing the unique properties of quantum mechanics to enhance the explainability of complex algorithms.

•Aug 28, 2026•0 citations

Topological quantum computing: comprehensive overview and theoretical foundations

Mateo Pabón Barbery

The apparent computational power of Quantum computers suggests a significant speed- up in calculations by leveraging the principles of superposition and entanglement, proper of Quantum Mechanics. However, the quantum information stored is very fragile to thermal excitations (also referred to as noise) and accuracy errors when information is processed via quantum logical gates. Many research areas develop techniques to correct and mitigate such errors; however, progress on the scalability and efficiency of quantum chips is slow. On the other hand, a relatively new technology has been proposed, directly targeting the prob- lem of decoherence by an inherently fault-tolerant quantum processor, Topological quantum Computing (TQC). In this overview, we trace State of the Art, the fundamental concepts, and the theoretical framework to understand systematically the physical consequence of its constituent qubits, non-Abelian anyons, and how to perform computation. The notion of topologically ordered states is built from a toy model, the Toric code, to a physical system exhibiting topological states, the Quantum Hall Effect (QHE). Once topological order is de- rived, the connection of non-Abelian anyons as qubits is bridged by a qualitative explanation, and the comprehension of the fundamental pillars of TQC flows more naturally. Concepts are reviewed under a comprehensive perspective, using clear language, without repetitive expla- nations found in other sources, and at a technisism level readable for a profile with a strong basic Quantum Mechanics background. Finally, a temporal sequence of the most cited and important achievements on topologically ordered systems and states with the perspective on building the first topological quantum computer closes this document, offering a wide picture of today’s state of the art on Topological Quantum Computing.

•May 1, 2025•0 citations
Large language models (LLMs) achieve remarkable predictive capabilities but remain opaque in their internal reasoning, creating a pressing need for more interpretable artificial intelligence. Here, we propose bridging this explanatory gap by drawing on concepts from topological quantum computing (TQC), specifically the anyonic frameworks arising from SU(2)k theories. Anyons interpolate between fermions and bosons, offering a mathematical language that may illuminate the latent structure and decision-making processes within LLMs. By examining how these topological constructs relate to token interactions and contextual dependencies in neural architectures, we aim to provide a fresh perspective on how meaning and coherence emerge. After eliciting insights from ChatGPT and exploring low-level cases of SU(2)k models, we argue that the machinery of modular tensor categories and topological phases could inform more transparent, stable, and robust AI systems. This interdisciplinary approach suggests that quantum-theoretic principles may underpin a novel understanding of explainable AI.
This paper presents a novel framework that integrates artificial intelligence with superalgebraic structures to simulate topological quantum computation (TQC) in systems governed by Lie superalgebras such as osp(1∣2) and sl(2∣1). By combining symbolic algebra, modular tensor category theory, and generative AI models—including variational autoencoders and diffusion models—the proposed system enables accurate, scalable simulation of non-Abelian anyonic braiding and fusion operations within graded symmetry constraints. The framework encodes superalgebraic invariants and topological rules into neural architectures, allowing physically valid and symmetry-preserving generation of braid paths and fusion outcomes. Experimental results demonstrate high fidelity, topological consistency, and robustness against noise, with successful emulation on quantum hardware platforms such as IBM Q and IonQ. This research opens new avenues for fault-tolerant, algebraically informed quantum simulation, circuit synthesis, and adaptive control in next-generation quantum technologies. Keywords: topological quantum computation, superalgebra, Lie superalgebras, modular tensor categories, osp(1∣2), sl(2∣1), anyons, braiding, fusion rules, symbolic AI, generative models, quantum simulation, quantum invariants, diffusion models, fault-tolerant quantum computing
The rapid advancement of Artificial Intelligence (AI) has heightened concerns about the opacity of decision-making processes in complex models, particularly deep neural networks. This research explores a novel paradigm that integrates quantum computing principles into Explainable AI (XAI) to enhance interpretability without compromising predictive accuracy. The study introduces a Quantum-inspired Interpretable Model (QIIM) framework that leverages Hilbert space embeddings, unitary transformations, and operator-based learning to represent knowledge in a mathematically transparent form. The proposed model computes interpretability through the expectation values of observable operators, enabling the decomposition of decisions into quantifiable, human-understandable components. To capture hierarchical relationships, a Tensor Network Interpretable Model (TNIM) is further developed, offering scalable insights into complex dependencies among features. Experimental evaluations—performed on benchmark datasets for decision-making tasks—demonstrate that the quantum-inspired models achieve competitive accuracy while significantly improving local and global interpretability metrics compared to classical XAI techniques. The findings underscore the potential of quantum formalism as a new foundation for transparent AI systems, bridging the gap between computational efficiency and explainability. This study contributes to both theoretical understanding and practical advancement in interpretable machine learning, paving the way for ethically aligned, transparent, and human-trustworthy AI-driven decision support systems.
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.
Topological quantum computation (TQC) is a new fault-tolerant approach to quantum information, where computations are carried out by braiding particles called anyons. Anyons are quasiparticles that exist in 2 + 1 dimensions and are neither bosons or fermions. Modular tensor categories capture the structure of anyon systems and thus serve as models for topological quantum computation. However, program of using category theory to find higher-level structures and protocols has yet to be applied to TQC due to the difficulty of working with modular tensor categories. This difficulty could be greatly mitigated by the development of a computer algebra system to represent such categories. Thus, a computer algebra system for representing modular tensor categories within the symmetric monoidal 2-category 2Vect was developed. A general representation for 2Vect is described. This involves extending basic linear algebra operations to handle matrices of zero-dimension and 2-matrices (matrices of matrices). Then, representations for the 0-cells, 1-cells, and 2-cells of 2Vect are found. Due to the chosen representation, various structural isomorphisms are required to ensure equations expected of 1-categories hold in the 2-categories setting. These structural isomorphisms are explicitly constructed. In order to identify special categories, such as modular tensor categories, a diagrammatic language of monoidal categories is extended for 2-categories. This language is used to construct the axioms for these special categories within 2Vect. Finally, a way of implementing these axioms within 2Vect in the computer algebra system is described. This system will now be used for the investigation of higher-level structures within modular tensor categories to better understand the structure of topological quantum computing.
The increasing deployment of Artificial Intelligence (AI) systems across various domains necessitates a deeper understanding of their decision-making processes. Current explainable AI (XAI) techniques often struggle to provide truly transparent and reliable explanations, particularly for complex models like deep neural networks. This paper proposes a novel approach to algorithmic transparency and XAI leveraging concepts from quantum information theory. Specifically, we explore the potential of quantum entanglement and mutual information to represent and analyze AI model decisions in a fundamentally different way. Our framework represents model outputs as quantum states and investigates the correlations between these states and the input data. This analysis aims to identify the key factors driving the model's decision and provide a more intuitive and understandable explanation. We demonstrate that utilizing quantum information theory can offer a richer and more robust approach to XAI than traditional methods, potentially addressing limitations related to interpretability and trust in AI systems. This work lays the groundwork for a new paradigm in AI transparency, utilizing the unique properties of quantum mechanics to enhance the explainability of complex algorithms.
The apparent computational power of Quantum computers suggests a significant speed- up in calculations by leveraging the principles of superposition and entanglement, proper of Quantum Mechanics. However, the quantum information stored is very fragile to thermal excitations (also referred to as noise) and accuracy errors when information is processed via quantum logical gates. Many research areas develop techniques to correct and mitigate such errors; however, progress on the scalability and efficiency of quantum chips is slow. On the other hand, a relatively new technology has been proposed, directly targeting the prob- lem of decoherence by an inherently fault-tolerant quantum processor, Topological quantum Computing (TQC). In this overview, we trace State of the Art, the fundamental concepts, and the theoretical framework to understand systematically the physical consequence of its constituent qubits, non-Abelian anyons, and how to perform computation. The notion of topologically ordered states is built from a toy model, the Toric code, to a physical system exhibiting topological states, the Quantum Hall Effect (QHE). Once topological order is de- rived, the connection of non-Abelian anyons as qubits is bridged by a qualitative explanation, and the comprehension of the fundamental pillars of TQC flows more naturally. Concepts are reviewed under a comprehensive perspective, using clear language, without repetitive expla- nations found in other sources, and at a technisism level readable for a profile with a strong basic Quantum Mechanics background. Finally, a temporal sequence of the most cited and important achievements on topologically ordered systems and states with the perspective on building the first topological quantum computer closes this document, offering a wide picture of today’s state of the art on Topological Quantum Computing.