2025/03/04 by Abdul Basit, Basit, Abdul, Nouhaila Innan +11 · 3 citations
Computer Science · #68T50 (Primary) #Artificial Intelligence (cs.AI) #Computational Physics and Python Applications #FOS: Computer and information sciences #FOS: Physical sciences #I.2.7 #Quantum Computing Algorithms and Architecture #Quantum Physics (quant-ph) #Software Engineering (cs.SE)
paper · pdf · doi:10.48550/arxiv.2503.02497
openalex publication_date 2025/03/04 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28
Large Language Models (LLMs) offer powerful capabilities in code generation, natural language understanding, and domain-specific reasoning. Their application to quantum software development remains limited, in part because of the lack of high-quality datasets both for LLM training and as dependable knowledge sources. To bridge this gap, we introduce PennyLang, an off-the-shelf, high-quality dataset of 3,347 PennyLane-specific quantum code samples with contextual descriptions, curated from textbooks, official documentation, and open-source repositories. Our contributions are threefold: (1) the creation and open-source release of PennyLang, a purpose-built dataset for quantum programming with PennyLane; (2) a framework for automated quantum code dataset construction that systematizes curation, annotation, and formatting to maximize downstream LLM usability; and (3) a baseline evaluation of the dataset across multiple open-source and commercial models, including ablation studies, all conducted within a retrieval-augmented generation (RAG) pipeline. Using PennyLang with RAG substantially improves performance: for example, Qwen 7B's success rate rises from 8.7% without retrieval to 41.7% with full-context augmentation, and LLaMa 4 improves from 78.8% to 84.8%, while also reducing hallucinations and enhancing quantum code correctness. Moving beyond Qiskit-focused studies, we bring LLM-based tools and reproducible methods to PennyLane for advancing AI-assisted quantum development.