Research Summary: Reducing Barriers to Academic Support: Evaluating a Course-Specific RAG System for Addressing Help-Seeking Disparities in Higher Education

Access to academic support is a significant factor in student success, but its availability and utilization are unevenly distributed among students due to factors such as anxiety, fear of judgment, and lack of confidence. General-purpose generative AI tools are often used but can be inaccurate or lack context. This research introduces and evaluates 'Beacon,' a course-specific Retrieval-Augmented Generation (RAG) system designed to offer private, immediate, and module-aligned academic assistance, aiming to mitigate these disparities.

Why it matters

This development addresses a critical challenge in educational equity and student success by proposing a technology-driven solution to academic support disparities. The integration of tailored AI systems could significantly enhance learning outcomes and resource utilization across educational institutions, promoting more inclusive and effective learning environments.

Key insights

• Unequal access to academic support is a primary determinant of student success.
• Student hesitation in seeking help stems from anxiety, fear of judgment, uncertainty, or low confidence.
• Disparities in help-seeking are particularly pronounced in cognitively demanding fields like computing education.
• General-purpose generative AI tools are frequently used but often deliver inaccurate or contextually inappropriate responses.
• The study introduces 'Beacon,' a course-specific RAG system, as a potential solution to address these disparities.
• Beacon aims to provide private, immediate, and module-aligned support, suggesting a tailored approach is beneficial.

Source

arXiv — Computers and Society — https://arxiv.org/abs/2609.21600