TrueGradeAI: Retrieval-Augmented and Bias-Resistant AI for Transparent and Explainable Digital Assessments

This paper introduces TrueGradeAI, an AI-driven digital examination framework that directly addresses the shortcomings of traditional paper assessments, namely excessive paper usage, logistical complexity, grading delays, and evaluator bias. The system preserves natural handwriting by capturing stylus input on secure tablets and applying transformer-based optical character recognition for transcription. Evaluation is performed through a retrieval-augmented pipeline that integrates faculty solutions, cache layers, and external references, enabling a large language model to assign scores with explicit, evidence-linked reasoning. By combining handwriting preservation with scalable and transparent evaluation, the framework reduces environmental costs, accelerates feedback cycles, and progressively builds a reusable knowledge base, while explicitly working to mitigate grading bias and ensure fairness in assessment. Despite advances in digital infrastructure, most institutions continue to rely on paper-based examinations as their primary mode of assessment.