Quantum Program Linting with LLMs: Emerging Results from a Comparative Study

TL;DR

Quantum program linting remains challenging due to evolving programming practices. The authors introduce LintQ-LLM, an LLM-based linting tool, and compare it to the CodeQL-based LintQ on real-world Qiskit code, finding that LintQ-LLM can match or exceed static-analysis performance in terms of precision ($\$70\%\$) and recall ($\$65\%\$) while offering improved problem localization and richer explanations. The study demonstrates the adaptability of LLM-driven linting to new quantum frameworks and outlines opportunities for hybrid pipelines that combine deterministic static analyses with context-aware, feedback-driven capabilities. Collectively, this work lays groundwork for more scalable and user-friendly quantum software quality assurance tools that can evolve with the field. Future directions include enhancing data-flow understanding, cross-framework generalization, and interactive, explainable linting powered by LLMs.

Abstract

Ensuring the quality of quantum programs is increasingly important; however, traditional static analysis techniques are insufficient due to the unique characteristics of quantum computing. Quantum-specific linting tools, such as LintQ, have been developed to detect quantum-specific programming problems; however, they typically rely on manually crafted analysis queries. The manual effort required to update these tools limits their adaptability to evolving quantum programming practices. To address this challenge, this study investigates the feasibility of employing Large Language Models (LLMs) to develop a novel linting technique for quantum software development and explores potential avenues to advance linting approaches. We introduce LintQ-LLM, an LLM-based linting tool designed to detect quantum-specific problems comparable to those identified by LintQ. Through an empirical comparative study using real-world Qiskit programs, our results show that LintQ-LLM is a viable solution that complements LintQ, with particular strengths in problem localization, explanation clarity, and adaptability potential for emerging quantum programming frameworks, thus providing a basis for further research. Furthermore, this study discusses several research opportunities for developing more advanced, adaptable, and feedback-aware quantum software quality assurance methods by leveraging LLMs.

Figures (3)

• Figure 1: An overview of the data flow in LintQ-LLM.
• Figure 2: Prompt template. ?param? indicates a parameter in the template.
• Figure 3: Prompt description of the double measurement problem (DoubleMeas in Table \ref{['tab:lintq problems']}). We reuse the problem description from the LintQ paper PaltenghiP24.