LLM-based Automated Grading with Human-in-the-Loop

TL;DR

This paper introduces GradeHITL, a human-in-the-loop framework leveraging large language models to improve automatic short answer grading accuracy by dynamically incorporating human expertise, surpassing existing automated methods.

Contribution

The paper presents a novel LLM-based human-in-the-loop approach for automated grading that adaptively refines rubrics with human input, achieving higher accuracy than prior fully automated methods.

Findings

GradeHITL outperforms existing automated grading methods.

Incorporating human feedback improves grading accuracy.

The approach approaches human-level grading performance.

Abstract

The rise of artificial intelligence (AI) technologies, particularly large language models (LLMs), has brought significant advancements to the field of education. Among various applications, automatic short answer grading (ASAG), which focuses on evaluating open-ended textual responses, has seen remarkable progress with the introduction of LLMs. These models not only enhance grading performance compared to traditional ASAG approaches but also move beyond simple comparisons with predefined "golden" answers, enabling more sophisticated grading scenarios, such as rubric-based evaluation. However, existing LLM-powered methods still face challenges in achieving human-level grading performance in rubric-based assessments due to their reliance on fully automated approaches. In this work, we explore the potential of LLMs in ASAG tasks by leveraging their interactive capabilities through a human-in-the-loop (HITL) approach. Our proposed framework, GradeHITL, utilizes the generative properties of LLMs to pose questions to human experts, incorporating their insights to refine grading rubrics dynamically. This adaptive process significantly improves grading accuracy, outperforming existing methods and bringing ASAG closer to human-level evaluation.