AI-Powered Resume Evaluation System: A Review

Abstract: In the current hiring process, most companies use Applicant Tracking Systems (ATS) to select candidates based on specific keywords and formatting rules. Although these systems are efficient, they often miss qualified individuals whose resumes are not perfectly formatted, creating a challenge for many job seekers. This paper introduces an intelligent framework that uses a Large Language Model (LLM), specifically Mistral-7B-Instruct-v0.2, to improve the job application and career development process. The system is built on four main functions: (1) extracting structured data from PDF resumes, (2) assessing ATS compatibility using a deep understanding of job descriptions, (3) identifying trending skills based on a candidate's career goals, and (4) recommending relevant industry certifications to enhance their professional profiles. The case study results show that the LLM-based system provides more personalized, insightful, and effective feedback compared to traditional ATS systems. This research demonstrates how artificial intelligence can make career advisory services more accessible, providing data-driven guidance that helps job seekers navigate the competitive job market with more confidence and success.