Authors : Sankaran Ramesh Kumar; M. A. Afsheen Sultana; M. D. Bilal Ahmed; Yedida Navya Sri Lakshmi Indu; Sangramjeet Ghosh

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/25wrczbt

DOI : https://doi.org/10.38124/ijisrt/26apr1104

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The integration of Generative Artificial Intelligence (GenAI) into higher education has precipitated a dual crisis: the exponential increase in faculty workload regarding assessment scalability and the destabilization of traditional academic integrity verification methods. This paper introduces the proposed system, an automated academic evaluation platform designed to address these challenges through a unified, immutable assessment pipeline. Unlike traditional Learning Management Systems (LMS) that function primarily as repositories, the proposed system employs Large Language Models (LLMs) to automate the entire grading lifecycle, from submission to feedback generation, while simultaneously performing rigorous authorship verification. The system enforces a single-submission policy to streamline administrative workflows and generates immutable, audit-ready reports containing scoring rationale and AIgenerated content likelihood. The system architecture, scoring methodology, and a multi-layered integrity detection approach based on stylometry and machine learning classifiers are described. Simulated performance results suggest that the proposed system mitigates the subjective variability of human grading while offering a scalable solution to the integrity challenges posed by unrestricted GenAI access.

Keywords : Automated Systems, Artificial Intelligence, Human-Computer Interaction, Large Language Models, Natural Language Processing.

References :

1. R. Kadel, B. K. Mishra, S. Shailendra, S. Abid, M. Rani, and S. P. Mahato, "Crafting tomorrow’s evaluations: Assessment design strategies in the era of generative AI," arXiv preprint arXiv:2405.01805, 2024.
2. S. K. Larsen, "Creating large language model resistant exams: Guidelines and strategies," arXiv preprint arXiv:2304.12203, 2023.
3. Z. Tian, A. Liu, L. Esbenshade, S. Sarkar, Z. Zhang, K. He, and M. Sun, "Implementation considerations for automated AI grading of student work, "arXiv preprint arXiv:2506.07955, 2025."
4. T. Sağlam and L. Schmid, "Evaluating software plagiarism detection in the age of AI: Automated obfuscation and lessons for academic integrity," arXiv preprint arXiv:2505.20158, 2025.
5. Y. Zhong, J. Hao, M. Fauss, C. Li, and Y. Wang, "AI-generated essays: Characteristics and implications on automated scoring and academic integrity," arXiv preprint arXiv:2410.17439, 2024.
6. G. Ardito, "Contra generative AI detection in higher education assessments," arXiv preprint arXiv:2312.05241, 2023.
7. A. Najjar, H. I. Ashqar, O. A. Darwish, and E. Hammad, "Detecting AI-generated text in educational content: Leveraging machine learning and explainable AI for academic integrity," arXiv preprint arXiv:2501.03203, 2025.
8. H. Albaqami, M. A. Ayub, N. Ahmad, Y. Ahmad, M. M. Alqahtani, A. M. Algamdi, A. Owaidah, and K. Ahmad, "Stylometry analysis of human and machine text for academic integrity," ar Xiv preprint arXiv:2601.01225, 2026.
9. R. Shekhar, S. Agarwal, P. Bordoloi, Y. Shah, T. Anvekar, and V. Gupta, "DoPE: Decoy oriented perturbation encapsulation human- readable, AI-hostile documents for academic integrity," arXiv preprint arXiv:2601.12505, 2026.
10. T. Lancaster, "A large language model supported synthesis of contemporary academic integrity research trends," arXiv preprint arXiv:2401.03481, 2024.