SteLLA: A Structured Grading System Using LLMs with RAG

TL;DR

This paper introduces SteLLA, a novel structured grading system that leverages Retrieval Augmented Generation with LLMs to improve automated short answer grading accuracy and provide detailed feedback, aligning closely with human grading.

Contribution

The paper proposes a new LLM-based grading system using RAG to extract structured info and evaluate answers, enhancing reliability and feedback quality in ASAG tasks.

Findings

Achieves substantial agreement with human graders.

Provides detailed breakdown of grades and feedback.

GPT-4 effectively captures facts but may infer too much.

Abstract

Large Language Models (LLMs) have shown strong general capabilities in many applications. However, how to make them reliable tools for some specific tasks such as automated short answer grading (ASAG) remains a challenge. We present SteLLA (Structured Grading System Using LLMs with RAG) in which a) Retrieval Augmented Generation (RAG) approach is used to empower LLMs specifically on the ASAG task by extracting structured information from the highly relevant and reliable external knowledge based on the instructor-provided reference answer and rubric, b) an LLM performs a structured and question-answering-based evaluation of student answers to provide analytical grades and feedback. A real-world dataset that contains students' answers in an exam was collected from a college-level Biology course. Experiments show that our proposed system can achieve substantial agreement with the human grader while providing break-down grades and feedback on all the knowledge points examined in the problem. A qualitative and error analysis of the feedback generated by GPT4 shows that GPT4 is good at capturing facts while may be prone to inferring too much implication from the given text in the grading task which provides insights into the usage of LLMs in the ASAG system.