Optimizing Resume Design for ATS Compatibility: A Large Language Model Approach

Abstract

The modern hiring process increasingly relies on Application Tracking Systems (ATS) to sort and evaluate resumes based on organizational preferences. However, many skilled and competent candidates fail to craft resumes that are ATS optimized, leading to missed opportunities. This study explores the potential of Large Language Models (LLMs) to enhance ATS compatibility in resumes. Using Natural Language Processing (NLP) techniques, LLMs analyze resumes to identify errors, recommend suitable keywords, enhance semantic alignment, and format content to meet ATS requirements. Evaluation results demonstrate that imple menting the model's suggested changes significantly improves ATS scores. This ap proach bridges the gap between job seekers and automated recruiting systems, empowering individuals to enhance their resumes effectively. By leveraging LLMs, job seekers gain a powerful tool to align their resumes with employer expectations, increasing their chances of success in the hiring process. This study highlights how LLMs can transform the recruitment landscape, improving access to employment and redefining traditional hiring practices