Metraipolis › archive › dc_89f6d0da3bb3
SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models — arXiv:2609.37134
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37134
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:26:56.388Z
- SHA-256 of the archived text
1cba405affb9a79440acede04057a9c57495c6fe118a899b7d0ee02a3884a25a- Stable URL of this page
https://metraipolis.com/documento/dc_89f6d0da3bb3
How to cite
SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models — arXiv:2609.37134 — arXiv (en), https://arxiv.org/abs/2609.37134 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89f6d0da3bb3 (Metraipolis archive dc_89f6d0da3bb3, sha256 1cba405affb9a79440acede04057a9c57495c6fe118a899b7d0ee02a3884a25a)
BibTeX
@misc{dc89f6d0da3bb3,
title = {SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models — arXiv:2609.37134},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37134},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89f6d0da3bb3; sha256 1cba405affb9a79440acede04057a9c57495c6fe118a899b7d0ee02a3884a25a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37134. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Frozen language models (LMs) are increasingly used as fixed feature extractors for downstream reranking, scoring, and preference modeling, raising a practical question: how should a compact module represent interactions among features in a fixed low-dimensional bottleneck? Common linear and low-rank adapters remain linear at the adaptation module itself, whereas explicit second-order alternatives introduce pairwise interactions through direct parameterization or predefined factorizations. We propose SQUARE, a Structured QUAntum REpresentation adapter that amplitude-encodes the bottleneck vector, applies a parameterized quantum circuit, and measures the resulting state. We show that each basis-probability feature is exactly a normalized quadratic form in the bottleneck coordinates, while the additional Pauli-$Z$ readouts are signed linear combinations of these probabilities. The measured map can therefore parameterize interactions over $O(d^2)$ coordinate pairs through a small set of shared circuit parameters, where $d$ is the bottleneck dimension. It provides a structured parameterization within, rather than beyond, the classical normalized-quadratic feature class. In a disjoint same-pipeline evaluation over eight GLUE-derived controlled interaction tasks and five shared seeds, SQUARE achieves an average test accuracy of $0.7565$, compared with $0.7355$ for an affine normalized-quadratic predictor, $0.7271$ for the evaluated parameter-matched Givens mixing model, $0.6817$ for an MLP, and $0.6155$ for a frozen-circuit control. Under reduced supervision, it also shows consistent gains over the strongest evaluated classical comparator, with the same qualitative pattern across multiple frozen LM backbones. All circuit experiments use simulation, while the learned feature map can be evaluated exactly in batched PyTorch without quantum hardware. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Quantum Physics (quant-ph) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.37134 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.948Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).