Beyond Grading Accuracy: Exploring Alignment of TAs and LLMs

TL;DR

This study evaluates open-source LLMs for grading UML class diagrams, comparing their performance to TAs at the criterion level, and demonstrates their potential to support automated grading with high accuracy and correlation.

Contribution

It introduces a criterion-level grading pipeline using open-source LLMs for UML diagrams, addressing transparency and cost issues in automated assessment.

Findings

Per-criterion accuracy up to 88.56%

Pearson correlation up to 0.78 with human grades

Optimal model combining best LLMs approaches TA performance

Abstract

In this paper, we investigate the potential of open-source Large Language Models (LLMs) for grading Unified Modeling Language (UML) class diagrams. In contrast to existing work, which primarily evaluates proprietary LLMs, we focus on non-proprietary models, making our approach suitable for universities where transparency and cost are critical. Additionally, existing studies assess performance over complete diagrams rather than individual criteria, offering limited insight into how automated grading aligns with human evaluation. To address these gaps, we propose a grading pipeline in which student-generated UML class diagrams are independently evaluated by both teaching assistants (TAs) and LLMs. Grades are then compared at the level of individual criteria. We evaluate this pipeline through a quantitative study of 92 UML class diagrams from a software design course, comparing TA grades against assessments produced by six popular open-source LLMs. Performance is measured across individual criterion, highlighting areas where LLMs diverge from human graders. Our results show per-criterion accuracy of up to 88.56% and a Pearson correlation coefficient of up to 0.78, representing a substantial improvement over previous work while using only open-source models. We also explore the concept of an optimal model that combines the best-performing LLM per criterion. This optimal model achieves performance close to that of a TA, suggesting a possible path toward a mixed-initiative grading system. Our findings demonstrate that open-source LLMs can effectively support UML class diagram grading by explicitly identifying grading alignment. The proposed pipeline provides a practical approach to manage increasing assessment workloads with growing student counts.