Data verification is the future of quantum computing copilots
File(s)
Accepted version
Author(s)
Song, Junhao
Bi, Ziqian
Chia, Xinliang
Knottenbelt, William
Cao, Yudong
Type
Conference Paper
Abstract
Quantum program generation demands a level of precision that may not be compatible with the statistical reasoning carried out in the inference of large language models (LLMs). Hallucinations are mathematically inevitable and not addressable by scaling, which leads to infeasible solutions. We argue that architectures prioritizing verification are necessary for quantum copilots and AI automation in domains governed by constraints. Our position rests on three key points: verified training data enables models to internalize precise constraints as learned structures rather than statistical approximations; verification must constrain generation rather than filter
outputs, as valid designs occupy exponentially shrinking sub-spaces; and domains where physical laws impose correctness criteria require verification embedded as architectural primitives. Early experiments showed LLMs without data verification could only achieve a maximum accuracy of 79% in circuit optimization. Our positions are formulated as quantum computing and AI4Research community imperatives, calling for elevating verification from afterthought to architectural foundation in AI4Research.
outputs, as valid designs occupy exponentially shrinking sub-spaces; and domains where physical laws impose correctness criteria require verification embedded as architectural primitives. Early experiments showed LLMs without data verification could only achieve a maximum accuracy of 79% in circuit optimization. Our positions are formulated as quantum computing and AI4Research community imperatives, calling for elevating verification from afterthought to architectural foundation in AI4Research.
Date Acceptance
2025-12-12
Citation
40th Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2026)
Publisher
AAAI
Journal / Book Title
40th Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2026)
Copyright Statement
Copyright © 2025, Association for the Advancement of Artificial Intelligence. This paper is embargoed until publication.
Identifier
https://doi.org/10.48550/arXiv.2602.04072
Source
AAAI 2026 Workshop on AI for Scientific Research
Publication Status
Accepted
Start Date
2026-01-20
Coverage Spatial
Singapore