Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education
This research suggests LLMs could support low-stakes formative assessments in K-12 education, though it is incremental as it builds on prior findings about GPT-4's grading capabilities.
The study evaluated how well Large Language Models (LLMs) can grade short answer questions in K-12 education, finding that GPT-4 with few-shot prompting achieved a Kappa score of 0.70, close to human-level performance of 0.75.
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.