Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial Relations

The automation of resume screening is a critical component of modern recruitment processes, particularly in large organizations. Automated systems for resume screening typically involve various NLP tasks to streamline candidate evaluation. This paper investigates the application of LLM models in aut...

Full description

Saved in:
Bibliographic Details
Main Author: Dan Peng
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11052269/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850087719284244480
author Dan Peng
author_facet Dan Peng
author_sort Dan Peng
collection DOAJ
description The automation of resume screening is a critical component of modern recruitment processes, particularly in large organizations. Automated systems for resume screening typically involve various NLP tasks to streamline candidate evaluation. This paper investigates the application of LLM models in automating labor education and skill assessment, focusing on optimizing workforce development through advanced language models. We propose a comprehensive framework for automating resume screening and grading, utilizing SOTA LLM models to enhance recruitment processes. The proposed system integrates information extraction and summarization tasks, leveraging LLMs for decision-making throughout the hiring process. Our experiments, conducted on a publicly available resume dataset, demonstrate significant improvements in efficiency and accuracy. The LLaMA2-13B model, achieves a ROUGE-1 score of 37.31, ROUGE-2 of 15.04, ROUGE-L of 36.99, and BLEU score of 13.82, significantly outperforming the baseline models such as FLAN-T5 and GPT-NeoX. These results highlight the potential of LLM-based systems in automating labor-related assessments, with the fine-tuned LLaMA2-13B model delivering up to 27% better performance than zero-shot models.
format Article
id doaj-art-20ad915ffc1d4c3e8f0df56509fb8dff
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-20ad915ffc1d4c3e8f0df56509fb8dff2025-08-20T02:43:10ZengIEEEIEEE Access2169-35362025-01-011311106411108610.1109/ACCESS.2025.358332411052269Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial RelationsDan Peng0https://orcid.org/0009-0006-7678-8238School of Marxism, China University of Mining and Technology, Beijing, ChinaThe automation of resume screening is a critical component of modern recruitment processes, particularly in large organizations. Automated systems for resume screening typically involve various NLP tasks to streamline candidate evaluation. This paper investigates the application of LLM models in automating labor education and skill assessment, focusing on optimizing workforce development through advanced language models. We propose a comprehensive framework for automating resume screening and grading, utilizing SOTA LLM models to enhance recruitment processes. The proposed system integrates information extraction and summarization tasks, leveraging LLMs for decision-making throughout the hiring process. Our experiments, conducted on a publicly available resume dataset, demonstrate significant improvements in efficiency and accuracy. The LLaMA2-13B model, achieves a ROUGE-1 score of 37.31, ROUGE-2 of 15.04, ROUGE-L of 36.99, and BLEU score of 13.82, significantly outperforming the baseline models such as FLAN-T5 and GPT-NeoX. These results highlight the potential of LLM-based systems in automating labor-related assessments, with the fine-tuned LLaMA2-13B model delivering up to 27% better performance than zero-shot models.https://ieeexplore.ieee.org/document/11052269/Skill assessmenthiring optimizationlarge language modelsknowledge graphNLP
spellingShingle Dan Peng
Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial Relations
IEEE Access
Skill assessment
hiring optimization
large language models
knowledge graph
NLP
title Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial Relations
title_full Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial Relations
title_fullStr Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial Relations
title_full_unstemmed Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial Relations
title_short Deep Learning-Driven Labor Education and Skill Assessment: A Big Data Approach for Optimizing Workforce Development and Industrial Relations
title_sort deep learning driven labor education and skill assessment a big data approach for optimizing workforce development and industrial relations
topic Skill assessment
hiring optimization
large language models
knowledge graph
NLP
url https://ieeexplore.ieee.org/document/11052269/
work_keys_str_mv AT danpeng deeplearningdrivenlaboreducationandskillassessmentabigdataapproachforoptimizingworkforcedevelopmentandindustrialrelations