• Nayana J
• Chethana V
• Rekha Rathod
• Pranoti Patil

Effective exam preparation requires structured learning, concept reinforcement, and personalized doubt resolution. Lumina AI is an artificial intelligence-driven educational assistant designed to enhance learning outcomes by generating topic-specific questions, providing step-by-step solutions, and enabling interactive doubt resolution. The system utilizes large language models fine-tuned on a curated dataset to dynamically generate medical entrance examination-level questions and detailed explanations, ensuring comprehensive subject mastery. Additionally, Lumina AI incorporates a follow-up questioning mechanism, allowing users to seek clarifications and strengthen their conceptual understanding. By leveraging natural language processing techniques, Model Fine-tuning techniques, prompt engineering the system offers a highly adaptive and personalized learning experience. Experimental results demonstrate the model’s effectiveness in generating high-quality questions and solutions, making it a valuable tool for self-paced learning and examination readiness. This paper presents the methodology, implementation, and evaluation of Lumina AI, highlighting its novel integration of domain-specific fine-tuning with interactive doubt resolution capabilities that distinguish it from existing systems.

Artificial intelligence, educational technology, exam preparation, interactive learning, large language models, natural language processing, question generation, step-by-step solutions.

" Lumina AI: A Topic-Specific Questions and Step-by-Step Solution Generation System with Doubt Resolution for NEET Aspirants", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.g690-g695, May-2025, Available :http://www.jetir.org/papers/JETIR2505771.pdf

" Lumina AI: A Topic-Specific Questions and Step-by-Step Solution Generation System with Doubt Resolution for NEET Aspirants", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppg690-g695, May-2025, Available at : http://www.jetir.org/papers/JETIR2505771.pdf