Integra: INclusive Technology for Enhanced Gradation and Review of Applicants

The true wealth of a company lies in the inclusivity and diversity among individuals. Addressing potential biases in resume screening is crucial to enhancing social and workplace well-being. We propose a solution called INTEGRA: Inclusive Technology for Enhanced Gradation and Review of Applicants. INTEGRA employs a Retrieval Augmented Generation (RAG) Fusion architecture to process resumes, effectively mitigating biases, via text summarization, before storing data. It includes a bias filter for queries to prevent their introduced by users, intentional or unintentional. Utilizing open-weight large language models (LLMs), INTEGRA ensures compliance with the AI Act and General Data Protection and Regulation (GDPR) law in EU , while maintaining data privacy within the organization, ensuring transparency and regulatory adherence. This approach aims to establish fairer HR practices, enhancing inclusivity and diversity within organizations. The thesis was developed in collaboration with the Innovation Labs at SACMI company and was presented at the Coling 2025 Conference.