Retrieval-Augmented Generation (RAG) systems rely on high-dimensional vector similarity search to retrieve relevant documents for large language models. However, classical nearest-neighbor methods face scalability limits dueto the "curse of dimensionality" and the computational cost of comparing massive vector sets.The authors propose a hybrid quantum-classical pipeline that leverages quantum computing for similarity evaluation.Experimental results on synthetic data demonstrate that the swap-test similarity estimates closely match classical dot products, and that clustering dramatically reduces search overhead.The present studies show the feasibility of quantum-enhanced retrieval: the quantum similarity scores approximate classical results within statistical error.We discuss accuracy, runtime trade-offs, and the challenges of state preparation in the Noisy Intermediate-Scale Quantum (NISQ) era.
Retrieval-Augmented Generation (RAG) systems rely on high-dimensional vector similarity search to retrieve relevant documents for large language models. However, classical nearest-neighbor methods face scalability limits dueto the "curse of dimensionality" and the computational cost of comparing massive vector sets.The authors propose a hybrid quantum-classical pipeline that leverages quantum computing for similarity evaluation.Experimental results on synthetic data demonstrate that the swap-test similarity estimates closely match classical dot products, and that clustering dramatically reduces search overhead.The present studies show the feasibility of quantum-enhanced retrieval: the quantum similarity scores approximate classical results within statistical error.We discuss accuracy, runtime trade-offs, and the challenges of state preparation in the Noisy Intermediate-Scale Quantum (NISQ) era.
Abstract Retrieval-Augmented Generation (RAG) has emerged as a powerful framework in natural language processing (NLP), integrating retrieval mechanisms with generative models to enhance information accuracy and contextual relevance. However, classical retrieval techniques face scalability bottlenecks and computational inefficiencies when handling large datasets. In this work, we introduce GroQ-Enhanced RAG (QRAG), a hybrid quantum-classical framework that leverages Grover’s search algorithm and GroQ-Rank (QAOA-based ranking) to enhance retrieval efficiency and optimization. QRAG employs Grover’s algorithm to accelerate query processing and utilizes GroQ for combinatorial ranking optimization, significantly reducing computational overhead. Empirical evaluations demonstrate that QRAG reduces retrieval latency by 40–50% compared to traditional RAG while improving response accuracy and scalability. By integrating quantum search and optimization techniques, GroQ-powered QRAG sets a new benchmark for efficient, high-fidelity information retrieval in NLP. While this study applies QRAG to RAG-based architectures, the proposed framework can be extended to other AI-driven retrieval-intensive applications, highlighting the transformative potential of quantum computing in large-scale language processing and information retrieval tasks.
The exponential growth of high-dimensional data in domains such as computer vision, genomics, and natural language processing has made similarity search a foundational yet challenging operation, primarily due to the "curse of dimensionality" that forces classical systems into computationally prohibitive exhaustive searches. This comprehensive report examines the transformative potential of integrating quantum computing to circumvent these classical bottlenecks. Quantum similarity search utilizes superposition and entanglement to evaluate exponential state spaces, promising quadratic speedups over classical algorithms. The analysis details the transition from classical indexing innovations like memory vectors to modalities of quantum data encoding, notably Amplitude Encoding and the Quantum Pixel Mamun, SM (2026) ……………………………………1 Quantum Similarity Search: Bridging Classical and Quantum Paradigms in High-Dimensional Data Retrieval Representation (QPIXL). It critically assesses vanguard quantum algorithms, particularly the Amplitude Estimation-based Quantum Inner Product (AE-QIP)—which provides a deterministic quadratic speedup over the prohibitive SWAP test—and Quantum Unsupervised Similarity Learning (QUSL), which uses evolutionary algorithms to optimize quantum circuits for complex tasks like image retrieval. Also available on Academia.edu: https://www.academia.edu/attachments/132047821/download_file?s=portfolio
This paper introduces a novel research direction for model-to-text/code transformations by leveraging Large Language Models (LLMs) that can be enhanced with Retrieval-Augmented Generation (RAG) pipelines. The focus is on quantum and hybrid quantum-classical software systems, where model-driven approaches can help reduce the costs and mitigate the risks associated with the heterogeneous platform landscape and lack of developers' skills. We validate one of the proposed ideas regarding generating code out of UML model instances of software systems. This Python code uses a well-established library, called Qiskit, to execute on gate-based or circuit-based quantum computers. The RAG pipeline that we deploy incorporates sample Qiskit code from public GitHub repositories. Experimental results show that well-engineered prompts can improve CodeBLEU scores by up to a factor of four, yielding more accurate and consistent quantum code. However, the proposed research direction can go beyond this through further investigation in the future by conducting experiments to address our other research questions and ideas proposed here, such as deploying software system model instances as the source of information in the RAG pipelines, or deploying LLMs for code-to-code transformations, for instance, for transpilation use cases.
Generating correct and executable quantum circuit code remains a significant barrier for both newcomers and experienced practitioners in quantum computing. While Large Language Models (LLMs) have shown promise in classical code generation, their application to quantum programming is hampered by limited domain-specific training data and the rapidly evolving nature of quantum software frameworks. In this work, we present Quantum-RAG, an extended Retrieval-Augmented Generation framework that couples a domain-specialized language model with a curated, multi-source knowledge corpus to produce Qiskit-based quantum circuit code. Our three-stage pipeline ingests documentation, educational notebooks, and research literature into a dense retrieval index and augments the generation model with the most relevant context at inference time. Evaluated on the Qiskit HumanEval benchmark, QuantumRAG achieves a Pass@1 of 0.4132, a Pass@3 of 0.6291, and a Pass@5 of 0.7020, surpassing the domain-adapted GraniteQiskit baseline by 101%, 72%, and 47 % at each respective threshold. These results demonstrate that retrieval-augmented approaches can substantially improve quantum code generation without expensive model retraining.
Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language Models (LLMs) dominate current practice, recent work has explored quantum-inspired alternatives motivated by the geometric properties of Hilbert-like spaces and their potential to encode richer semantic structure.
This paper presents an experimental framework for constructing quantum-inspired 1024-dimensional document embeddings based on overlapping windows and multi-scale aggregation. The pipeline combines semantic projections (e.g., EigAngle), circuit-inspired feature mappings, and optional teacher-student distillation, together with a fingerprinting mechanism for reproducibility and controlled evaluation.
We introduce a set of diagnostic tools for hybrid retrieval, including static and dynamic interpolation between BM25 and embedding-based scores, candidate union strategies, and a conceptual alpha-oracle that provides an upper bound for score-level fusion.
Experiments on controlled corpora of Italian and English documents across technical, narrative, and legal domains, using synthetic queries, show that BM25 remains a strong baseline, teacher embeddings provide stable semantic structure, and standalone quantum-inspired embeddings exhibit weak and unstable ranking signals. Distillation yields mixed effects, improving alignment in some cases but not consistently enhancing retrieval performance, while hybrid retrieval can recover competitive results when lexical and embedding-based signals are combined.
Overall, the results highlight structural limitations in the geometry of quantum-inspired embeddings, including distance compression and ranking instability, and clarify their role as auxiliary components rather than standalone retrieval representations.
Although the performance of LLMs on a wide variety of natural language processing problems demonstrates remarkable ability, hallucinated responses are introduced as one of the key weaknesses of LLMs, especially in knowledge-intensive applications, where fidelity to facts is paramount. While effective in reducing hallucinations, the context retrieved during the RAG operations is still very often suboptimal with respect to the external documents used in the retrieval stage, and being based on cosine similarity and nearest-neighbour search, these models typically do not return optimal context to support factual generation. The authors propose a five-stage solution, called Quantum-Enhanced Retrieval-Augmented Generation (QERAG), which combines the use of a quantum-inspired probability amplitude document ranking, a Context Utility Score (CUS) optimisation engine, and a Hallucination Verification Agent (HVA) based on a formal Hallucination Reduction Index (HRI). The Quantum Relevance Score (QRS) uses interference based, Amplitude Encoding on candidate Document Sets to yield a normalised relevance distribution that emphasises the relatively higher value generated in the discriminative context as compared to other locally similar passages in a document set. QERAG outperforms Standard LLM and Traditional RAG models on all five Natural benchmark across response accuracy, with a score of 92.8% vs. 74.3%, and hallucination rate, 4.3% vs. 18.2%, respectively. They achieve a significant overall improvement by using quantum-inspired retrieval layer, which achieves a 3.5-percentage-point reduction in hallucination rate when compared to cosine-similarity RAG, with this single layer showing more reduction than the rest of the pipeline layers. The results of an ablation study show the individual contribution of every pipeline stage, and the quantum-inspired retrieval layer exhibits the greatest reduction of a 3.5 percentage points over cosine-similarity RAG.