A PennyLane-Centric Dataset to Enhance LLM-based Quantum Code Generation using RAG
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908971687739392 |
|---|---|
| author | Basit, Abdul Innan, Nouhaila Asif, Muhammad Haider Shao, Minghao Kashif, Muhammad Marchisio, Alberto Shafique, Muhammad |
| author_facet | Basit, Abdul Innan, Nouhaila Asif, Muhammad Haider Shao, Minghao Kashif, Muhammad Marchisio, Alberto Shafique, Muhammad |
| contents | 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 \textit{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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02497 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A PennyLane-Centric Dataset to Enhance LLM-based Quantum Code Generation using RAG Basit, Abdul Innan, Nouhaila Asif, Muhammad Haider Shao, Minghao Kashif, Muhammad Marchisio, Alberto Shafique, Muhammad Software Engineering Artificial Intelligence Quantum Physics 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 \textit{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. |
| title | A PennyLane-Centric Dataset to Enhance LLM-based Quantum Code Generation using RAG |
| topic | Software Engineering Artificial Intelligence Quantum Physics |
| url | https://arxiv.org/abs/2503.02497 |