Augmented Fine-Tuned LLMs for Enhanced Recruitment Automation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Younes, Mohamed T., Walid, Omar, Shaban, Khaled, Hamdi, Ali, Hassan, Mai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915484025225216
author Younes, Mohamed T.
Walid, Omar
Shaban, Khaled
Hamdi, Ali
Hassan, Mai
author_facet Younes, Mohamed T.
Walid, Omar
Shaban, Khaled
Hamdi, Ali
Hassan, Mai
contents This paper presents a novel approach to recruitment automation. Large Language Models (LLMs) were fine-tuned to improve accuracy and efficiency. Building upon our previous work on the Multilayer Large Language Model-Based Robotic Process Automation Applicant Tracking (MLAR) system . This work introduces a novel methodology. Training fine-tuned LLMs specifically tuned for recruitment tasks. The proposed framework addresses the limitations of generic LLMs by creating a synthetic dataset that uses a standardized JSON format. This helps ensure consistency and scalability. In addition to the synthetic data set, the resumes were parsed using DeepSeek, a high-parameter LLM. The resumes were parsed into the same structured JSON format and placed in the training set. This will help improve data diversity and realism. Through experimentation, we demonstrate significant improvements in performance metrics, such as exact match, F1 score, BLEU score, ROUGE score, and overall similarity compared to base models and other state-of-the-art LLMs. In particular, the fine-tuned Phi-4 model achieved the highest F1 score of 90.62%, indicating exceptional precision and recall in recruitment tasks. This study highlights the potential of fine-tuned LLMs. Furthermore, it will revolutionize recruitment workflows by providing more accurate candidate-job matching.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06196
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Augmented Fine-Tuned LLMs for Enhanced Recruitment Automation
Younes, Mohamed T.
Walid, Omar
Shaban, Khaled
Hamdi, Ali
Hassan, Mai
Computation and Language
This paper presents a novel approach to recruitment automation. Large Language Models (LLMs) were fine-tuned to improve accuracy and efficiency. Building upon our previous work on the Multilayer Large Language Model-Based Robotic Process Automation Applicant Tracking (MLAR) system . This work introduces a novel methodology. Training fine-tuned LLMs specifically tuned for recruitment tasks. The proposed framework addresses the limitations of generic LLMs by creating a synthetic dataset that uses a standardized JSON format. This helps ensure consistency and scalability. In addition to the synthetic data set, the resumes were parsed using DeepSeek, a high-parameter LLM. The resumes were parsed into the same structured JSON format and placed in the training set. This will help improve data diversity and realism. Through experimentation, we demonstrate significant improvements in performance metrics, such as exact match, F1 score, BLEU score, ROUGE score, and overall similarity compared to base models and other state-of-the-art LLMs. In particular, the fine-tuned Phi-4 model achieved the highest F1 score of 90.62%, indicating exceptional precision and recall in recruitment tasks. This study highlights the potential of fine-tuned LLMs. Furthermore, it will revolutionize recruitment workflows by providing more accurate candidate-job matching.
title Augmented Fine-Tuned LLMs for Enhanced Recruitment Automation
topic Computation and Language
url https://arxiv.org/abs/2509.06196