Smart Recruit: A Context-Aware Resume Parsing and Job Matching System

We presented Smart Recruit, a system combining layout-aware OCR, transformer-based NER, KG construction, GNN-based structural modeling, asymmetric preference modeling, and LIME-based explainability. All planned items (explain-ability, UI, backend, deployment, GAT enhancements, active learning) were implemented and validated . Future work: large-scale deployment, drift detection, privacy-preserving learning (federated / differential privacy), and public-benchmark evaluation.

[1]     J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019. [2]     N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using siamese BERT-networks,” in Proc. EMNLP, 2019. [3]     Y. Xu, M. Li, L. Cui, S. Huang, F. Wei, and M. Zhou, “LayoutLM: Pre-training of text and layout for document image understanding,” 2019. [Online]. Available: https://arxiv.org/abs/1912.13318. [4]     T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in Proc. ICLR, 2017. [5]     P. Velicˇkovic´ et al., “Graph attention networks,” in Proc. ICLR, 2018. [6]     Y. Du et al., “Quasi-metric learning for bilateral person-job fit,” IEEE Trans. Pattern Anal. Mach. Intell., 2025. [7]     M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you?: Explaining the predictions of any classifier,” in Proc. ACM SIGKDD, 2016. [8]     X. Li, H. Shu, Y. Zhai, Z. Lin, “A Method for Resume Information Extraction Using BERT-BiLSTM-CRF,” in Proc. ICCT, 2021. [9]     D. Pawade, T. Joshi, S. Parkhe, “Survey on Resume and Job Profile Matching System,” in Proc. ICAST, 2023. [10]    Z. Xiuyun, Y. Hualing, “Optimizing Job Matching Efficiency,” in Proc. CIPAE, 2024.