Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education

TL;DR

This study evaluates GPT-4's ability to grade K-12 short answer questions, finding it performs nearly at human level across subjects and grade levels, indicating potential for supporting formative assessments.

Contribution

It introduces a new dataset and demonstrates GPT-4's high accuracy in grading diverse student responses, advancing AI applications in educational assessment.

Findings

GPT-4 achieved a Kappa of 0.70, close to human 0.75.

Performance was consistent across Science and History subjects.

Results suggest LLMs can support formative assessment in K-12 education.

Abstract

This paper presents reports on a series of experiments with a novel dataset evaluating how well Large Language Models (LLMs) can mark (i.e. grade) open text responses to short answer questions, Specifically, we explore how well different combinations of GPT version and prompt engineering strategies performed at marking real student answers to short answer across different domain areas (Science and History) and grade-levels (spanning ages 5-16) using a new, never-used-before dataset from Carousel, a quizzing platform. We found that GPT-4, with basic few-shot prompting performed well (Kappa, 0.70) and, importantly, very close to human-level performance (0.75). This research builds on prior findings that GPT-4 could reliably score short answer reading comprehension questions at a performance-level very close to that of expert human raters. The proximity to human-level performance, across a variety of subjects and grade levels suggests that LLMs could be a valuable tool for supporting low-stakes formative assessment tasks in K-12 education and has important implications for real-world education delivery.