AI-Enabled grading with near-domain data for scaling feedback with human-level accuracy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Agarwal, Shyam, Moghimi, Ali, Haudek, Kevin C.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909942942793728
author Agarwal, Shyam
Moghimi, Ali
Haudek, Kevin C.
author_facet Agarwal, Shyam
Moghimi, Ali
Haudek, Kevin C.
contents Constructed-response questions are crucial to encourage generative processing and test a learner's understanding of core concepts. However, the limited availability of instructor time, large class sizes, and other resource constraints pose significant challenges in providing timely and detailed evaluation, which is crucial for a holistic educational experience. In addition, providing timely and frequent assessments is challenging since manual grading is labor intensive, and automated grading is complex to generalize to every possible response scenario. This paper proposes a novel and practical approach to grade short-answer constructed-response questions. We discuss why this problem is challenging, define the nature of questions on which our method works, and finally propose a framework that instructors can use to evaluate their students' open-responses, utilizing near-domain data like data from similar questions administered in previous years. The proposed method outperforms the state of the art machine learning models as well as non-fine-tuned large language models like GPT 3.5, GPT 4, and GPT 4o by a considerable margin of over 10-20% in some cases, even after providing the LLMs with reference/model answers. Our framework does not require pre-written grading rubrics and is designed explicitly with practical classroom settings in mind. Our results also reveal exciting insights about learning from near-domain data, including what we term as accuracy and data advantages using human-labeled data, and we believe this is the first work to formalize the problem of automated short answer grading based on the near-domain data.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI-Enabled grading with near-domain data for scaling feedback with human-level accuracy
Agarwal, Shyam
Moghimi, Ali
Haudek, Kevin C.
Computers and Society
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Constructed-response questions are crucial to encourage generative processing and test a learner's understanding of core concepts. However, the limited availability of instructor time, large class sizes, and other resource constraints pose significant challenges in providing timely and detailed evaluation, which is crucial for a holistic educational experience. In addition, providing timely and frequent assessments is challenging since manual grading is labor intensive, and automated grading is complex to generalize to every possible response scenario. This paper proposes a novel and practical approach to grade short-answer constructed-response questions. We discuss why this problem is challenging, define the nature of questions on which our method works, and finally propose a framework that instructors can use to evaluate their students' open-responses, utilizing near-domain data like data from similar questions administered in previous years. The proposed method outperforms the state of the art machine learning models as well as non-fine-tuned large language models like GPT 3.5, GPT 4, and GPT 4o by a considerable margin of over 10-20% in some cases, even after providing the LLMs with reference/model answers. Our framework does not require pre-written grading rubrics and is designed explicitly with practical classroom settings in mind. Our results also reveal exciting insights about learning from near-domain data, including what we term as accuracy and data advantages using human-labeled data, and we believe this is the first work to formalize the problem of automated short answer grading based on the near-domain data.
title AI-Enabled grading with near-domain data for scaling feedback with human-level accuracy
topic Computers and Society
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2512.04113