A Survey on AI-Based Answer Sheet Evaluation and Result Management Systems

Read full text Summarise with VIRAT
Authors: vaidehi kokare, Riyazahemed Jamadar Aayush Dhotre
Cited by: 0
References: 10

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Artificial Intelligence (AI) in teaching can transform traditional methods of assessment, particularly the methods of evaluation of the descriptive and open-ended responses of the students. Large language models (LLMs) can read, interpret and generate text in a human-like way, which means that automated grading systems can be both more scalable and objective than in the past when it was performed by human evaluators. Beyond accuracy, transparent, reliable and capable of producing actionable feedback post in accordance with pedagogical standards, many LLMs offer a black box design, which can actively raise concerns about fairness, interpretability and transparency, and the cost/benefit balance of processing speed and analytical depth can limit learners and institutions in their use. An emerging solution, which is the focus of a review in the present paper, is dual-process LLM frameworks of automated assessment. These hybrid systems are a combination of a bigger, more complex system that would perform more comprehensive rubric-based assessment and a system that would make detailed feedback with a slightly small model which could be used to score first assessments fast. To provide researchers and educators with a comprehensive outline of the development of reliable and efficient AI-powered assessment devices.

Fields of Study & Subjects

Artificial Intelligence in Education Educational Technology and Assessment Educational Technology and Pedagogy

Publication details

Journal / source
International Journal of Advanced Research in Science Communication and Technology
Pages
168–168
Publication date
26 March 2026
Language
EN