A Hybrid Approach for Job Recommendation Systems

This paper presents a hybrid approach to job recommendation that integrates traditional and Large Language Models to provide more relevant job recommendations. The methodology involves preprocessing CV and job description databases, followed by application processing with two different modules: one using traditional techniques for recommendations and the other with unguided LLMs. The final job recommendation or similarity score is determined by calculating the average of the similarity scores from both modules. This approach is validated by considering some example CVs and job descriptions from the IT field. Our results demonstrate the effectiveness of this hybrid approach for Job Recommendations.