Citation

Tahir, H. Ahmed and Tahir, Hamna and Tariq, Muhammad Ziad and Mahmud, Azwan (2025) XAI-enhanced HRM: Leveraging large language models for talent acquisition and management. In: 4th International Conference on Computer, Information Technology and Intelligent Computing, CITIC 2024, 23 July 2024 - 25 July 2024, Virtual, Online.

Full text not available from this repository.

Abstract

This paper explores Llama v2, an advanced large language model (LLM), for Human Resource Management (HRM). Llama v2’s sophisticated natural language processing (NLP) capabilities hold immense potential to revolutionize work- force planning and decision-making in HRM. However, addressing the ”black box” nature of LLMs is crucial for responsible implementation. Our research investigates how to leverage Llama v2 for predictive talent acquisition and management while incorporating Explainable Artificial Intelligence (XAI) techniques. By leveraging Llama v2’s pre- trained parameters and fine-tuning methodologies, we analyze diverse HR datasets (performance metrics, turnover rates, market trends, etc.). We employ tailored optimization techniques to extract actionable insights from unstructured data, facilitating accurate predictions of future talent needs. Our focus is on explainability and mitigating bias. We address technical parameters like model training, hyperparameter optimization, and feature selection specific to HRM, while simultaneously incorporating XAI methods to make Llama v2’s predictions interpretable. This ensures transparency and helps mitigate potential biases present in the training data that could lead to discriminatory practices. Additionally, our pro- posed method facilitates applicants by providing comprehensive feedback emails instead of regret emails if a candidate is not suitable. This allows applicants to further improve their skills and save time.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Black-box, Data science, Artificial intelligence, Natural language processing
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD28-70 Management. Industrial Management
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	04 Dec 2025 03:06
Last Modified:	13 Dec 2025 13:54
URII:	http://shdl.mmu.edu.my/id/eprint/14951

Downloads

Edit (login required)