Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement

2026-09-13

AI Summary

研究通过10量子位混合量子-经典变分电路解决自然语言处理中的同义句检测问题，对比经典模型表现出色且参数效率更高。

Abstract

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.

Problem

• quantum machine learning
• natural language processing
• paraphrase detection
• empirical validation

Innovation

• hybrid quantum-classical variational circuit
• parameter-efficient
• entanglement
• paraphrase detection
• adversarial robustness