Revolutionizing Talent Acquisition: A Comparative Study of Large Language Models in Resume Classification

The core aim of this study is to explore the capabilities of Large Language Models (LLMs) in resume classification, a pivotal task in talent acquisition and human resources management. This research seeks to surpass the constraints of traditional methods, which typically depend on elementary Natural Language Processing (NLP) strategies, by leveraging the advanced potential of LLMs. To achieve this, the study conducted a detailed empirical evaluation, testing a range of LLMs, including various versions of Text Davinci, GPT models, LLaMa and Flan T5 The methodology was thorough, integrating data preprocessing and text normalization to bolster the reliability and validity of the findings. The investigation provided a comparative analysis of the selected LLMs, concentrating on key performance indicators such as accuracy, precision, recall, and F1-Score. The findings reveal that LLMs, including the addition of Gemini, significantly improve upon conventional methods in resume classification tasks. This research not only offers deep insights into the utility and efficiency of LLMs in this field but also lays the groundwork for future explorations. Furthermore, it highlights the revolutionary impact of LLMs on revolutionizing talent acquisition and human resource management practices.