Metraipolis › archive › dc_94367defefd9
Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement — arXiv:2609.14529
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14529
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:16:59.368Z
- SHA-256 of the archived text
3638805194adad8ad5fa4941b9732d7591d52ae66e75b010bf68185d30163b52- Stable URL of this page
https://metraipolis.com/documento/dc_94367defefd9
How to cite
Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement — arXiv:2609.14529 — arXiv (en), https://arxiv.org/abs/2609.14529 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_94367defefd9 (Metraipolis archive dc_94367defefd9, sha256 3638805194adad8ad5fa4941b9732d7591d52ae66e75b010bf68185d30163b52)
BibTeX
@misc{dc94367defefd9,
title = {Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement — arXiv:2609.14529},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14529},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_94367defefd9; sha256 3638805194adad8ad5fa4941b9732d7591d52ae66e75b010bf68185d30163b52},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14529. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Rigorous empirical validation of quantum machine learning on natural language tasks remains scarce. We evaluate a 10-qubit hybrid quantum-classical variational circuit (2,148 parameters) for paraphrase detection across three benchmarks: MRPC, Quora Question Pairs (QQP), and adversarial PAWS. On QQP (n = 10 seeds), the circuit achieves 75.53% +/- 0.75%. accuracy, statistically outperforming parameter-matched classical baselines (DeepMLP: p = 0.015, Cohen's d = 1.20; F1: p < 0.001, d = 2.32) and surpassing DistilBERT-4bit with 31,191 fewer parameters. On MRPC the optimal 2-layer variant reaches 92% of BERT-base accuracy at 54,000 lower parameter cost. Circuit depth analysis reveals a dataset-depth scaling effect; entanglement analysis via the Meyer-Wallach measure identifies multi-qubit entanglement as the primary performance driver (r = 0.85 across four variants). Adversarial evaluation on PAWS reveals emergent robustness: 98.2% recall versus 81.6% classical (+16.6 pp, d = 1.24, p < 0.001), without adversarial training. These results constitute the first systematic parameter-matched multi-benchmark empirical validation of hybrid variational circuits for NLP. All results are from classical simulation; hardware validation is future work. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL). Categorie arXiv: Quantum Physics (quant-ph) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.14529 — 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 2026-10-15T22:51:10.017Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).