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

• URL: http://arxiv.org/abs/2609.14529v1
• Date: Sun, 13 Sep 2026 14:06:49 GMT
• Title: Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement
• Abstract summary: We evaluate a 10-qubit hybrid quantum-classical variational circuit for paraphrase detection.<n>On QQP the circuit achieves 75.53% +/- 0.75% accuracy.<n>On MRPC the optimal 2-layer variant reaches 92% of BERT-base accuracy at 54,000 lower parameter cost.<n>These results constitute the first systematic parameter-matched multi-benchmark empirical validation of hybrid variational circuits for NLP.
• Score: 0.05999777817331314
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• OQMD: Single-Qubit Rotation Control Improves Low-CNOT Multiclass Quantum Classification [4.669017653337737]
  This work studies Optimal Quantum Measurement Decoding (OQMD)<n>OQMD: optimizing how quantum outcomes are mapped to classical labels by training a readout layer before measurement.<n>Experiments use trainable triple single-qubit rotations as one concrete, hardware-native realization of OQMD.
  arXiv  Detail & Related papers  (2026-06-12T04:05:48Z)
• How Much Capacity Does EEG Denoising Need? Ultra-Compact Networks reveal Benchmark Saturation and Metric-Utility Gap [0.0]
  Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model capacity as the experimental variable.<n>We address both gaps by fixing architecture, loss, data split, and training recipe while sweeping only channel width from 1.05K to 40.26K parameters in a minimal depthwiseseparable convolutional U-Net.
  arXiv  Detail & Related papers  (2026-06-07T12:17:25Z)
• Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search [50.16356451328644]
  Proving Shannon-type entropy inequalities is a fundamental task in information theory.<n>We investigate whether small-scale large language models, fine-tuned on atomic proof steps, can automate this process.<n>We show that GPT-5.5 solves 1.7% samples under zero-shot prompting while Psitip solves 33.3% samples.
  arXiv  Detail & Related papers  (2026-06-04T05:43:12Z)
• Optimised Support Vector Regression for California Housing Price Prediction: The Critical Role of Feature Engineering and Hyperparameter Tuning [0.0]
  Support Vector Regression has been cited as one of the weakest performers on the California Housing benchmark dataset.<n>This paper examines whether the previously reported performance reflects experimental configuration choices rather than an inherent algorithmic limitation.<n> tuned SVR achieves a test R2 of 0.723, a 0.123-point absolute improvement over the previously reported SVR result.
  arXiv  Detail & Related papers  (2026-05-09T03:58:50Z)
• Relational Preference Encoding in Looped Transformer Internal States [0.0]
  We investigate how looped transformers encode human preference in their internal iteration states.<n>Using Ouro-2.6B-Thinking, a 2.6B- parameter looped transformer with iterative refinement, we extract hidden states from each loop iteration.<n>We train lightweight evaluator heads to predict human preference on the Anthropic HH-RLHF dataset.<n>Our pairwise evaluator achieves 95.2% test accuracy on 8,552 unseen examples, surpassing a full-batch L-BFGS probe (84.5%) while the base model remains completely frozen.
  arXiv  Detail & Related papers  (2026-04-10T20:00:49Z)
• DeepPrune: Parallel Scaling without Inter-trace Redundancy [53.62015294143274]
  Over 80% of parallel reasoning traces yield identical final answers, representing substantial wasted computation.<n>We propose DeepPrune, a novel framework that enables efficient parallel scaling through dynamic pruning.<n>Our work establishes a new standard for efficient parallel reasoning, making high-performance reasoning more efficient.
  arXiv  Detail & Related papers  (2025-10-09T17:24:54Z)
• Hybrid Quantum-Classical Model for Image Classification [0.0]
  This study presents a systematic comparison between hybrid quantum-classical neural networks and purely classical models across three benchmark datasets.<n>The hybrid models integrate parameterized quantum circuits with classical deep learning architectures, while the classical counterparts use conventional convolutional neural networks (CNNs)<n>Experiments were conducted over 50 training epochs for each dataset, with evaluations on validation accuracy, test accuracy, training time, computational resource usage, and adversarial robustness.
  arXiv  Detail & Related papers  (2025-09-14T09:55:00Z)
• Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning [126.84770886628833]
  Existing finetuning methods either tune all parameters of the pretrained model (full finetuning) or only tune the last linear layer (linear probing) We propose a new parameter-efficient finetuning method termed as SSF, representing that researchers only need to Scale and Shift the deep Features extracted by a pre-trained model to catch up with the performance full finetuning.
  arXiv  Detail & Related papers  (2022-10-17T08:14:49Z)
• Experimental Bayesian calibration of trapped ion entangling operations [48.43720700248091]
  We develop and characterize an efficient calibration protocol to automatically estimate and adjust experimental parameters of the widely used Molmer-Sorensen entangling gate operation. We experimentally demonstrate a median gate infidelity of $1.3(1)cdot10-3$, requiring only $1200pm500$ experimental cycles, while completing the entire gate calibration procedure in less than one minute.
  arXiv  Detail & Related papers  (2021-12-02T16:59:00Z)
• Non-Parametric Adaptive Network Pruning [125.4414216272874]
  We introduce non-parametric modeling to simplify the algorithm design. Inspired by the face recognition community, we use a message passing algorithm to obtain an adaptive number of exemplars. EPruner breaks the dependency on the training data in determining the "important" filters.
  arXiv  Detail & Related papers  (2021-01-20T06:18:38Z)
• ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning [91.13797346047984]
  We introduce ADAHESSIAN, a second order optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates. We show that ADAHESSIAN achieves new state-of-the-art results by a large margin as compared to other adaptive optimization methods.
  arXiv  Detail & Related papers  (2020-06-01T05:00:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.