A Trustworthy Explainable AI Framework for Automated Handwritten Subjective Answer Evaluation Using Document Intelligence and Large Language Models

MD Shamshad Ali; Praveen Kumar Kaithal; Arun Kumar Jhapate; Mohit Singh Tomar; Ritu Shrivastava

A Trustworthy Explainable AI Framework for Automated Handwritten Subjective Answer Evaluation Using Document Intelligence and Large Language Models

Author(s)	Mr. MD Shamshad Ali, Dr. Praveen Kumar Kaithal, Mr. Arun Kumar Jhapate, Dr. Mohit Singh Tomar, Ms. Ritu Shrivastava
Country	India
Abstract	Automated evaluation of handwritten subjective answers is challenging due to handwriting variability, OCR errors, and semantic diversity in student responses. Existing automated grading systems often lack transparency and interpretability, limiting their adoption in educational settings. This paper proposes a trustworthy Explainable Artificial Intelligence (XAI) framework for handwritten subjective answer evaluation using document intelligence and Large Language Models (LLMs). The framework employs image preprocessing and Optical Character Recognition (OCR) to extract textual content from handwritten answer sheets. Document intelligence techniques are utilized for answer segmentation and contextual understanding. A rubric-based evaluation module powered by LLMs assesses answer quality based on correctness, completeness, relevance, and coherence. Explainability mechanisms provide grading justifications and score interpretations to improve transparency and trust. The framework further incorporates fairness, robustness, and consistency analysis to ensure reliable assessment. Experimental results demonstrate the effectiveness of the proposed approach in achieving accurate and interpretable automated grading. The proposed system supports scalable and trustworthy AI-assisted educational assessment.
Keywords	Explainable AI, Document Intelligence, Handwritten Answer Evaluation, OCR, Large Language Models, Trustworthy AI, NLP, Rubric-Based Assessment.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 17, Issue 3, July-September 2026
Published On	2026-08-11

View / Download PDF File

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics	Join as a Reviewer Editors & Reviewers Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

A Trustworthy Explainable AI Framework for Automated Handwritten Subjective Answer Evaluation Using Document Intelligence and Large Language Models

Share this