English

Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUs

Computation and Language 2025-05-30 v1

Abstract

This study presents an efficient transformer-based question-answering (QA) model optimized for deployment on a 13th Gen Intel i7-1355U CPU, using the Stanford Question Answering Dataset (SQuAD) v1.1. Leveraging exploratory data analysis, data augmentation, and fine-tuning of a DistilBERT architecture, the model achieves a validation F1 score of 0.6536 with an average inference time of 0.1208 seconds per question. Compared to a rule-based baseline (F1: 0.3124) and full BERT-based models, our approach offers a favorable trade-off between accuracy and computational efficiency. This makes it well-suited for real-time applications on resource-constrained systems. The study includes systematic evaluation of data augmentation strategies and hyperparameter configurations, providing practical insights into optimizing transformer models for CPU-based inference.

Keywords

Cite

@article{arxiv.2505.22937,
  title  = {Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUs},
  author = {Ngeyen Yinkfu},
  journal= {arXiv preprint arXiv:2505.22937},
  year   = {2025}
}

Comments

This paper presents an efficient transformer-based question-answering model optimized for inference on a 13th Gen Intel i7 CPU. The proposed approach balances performance and computational efficiency, making it suitable for real-time applications on resource-constrained devices. Code for this paper is available upon request via email at nyinkfu@andrew.cmu.edu

R2 v1 2026-07-01T02:47:31.445Z