Saved in:
Bibliographic Details
Main Authors: Chu, Yucheng, He, Peng, Li, Hang, Han, Haoyu, Yang, Kaiqi, Xue, Yu, Li, Tingting, Krajcik, Joseph, Tang, Jiliang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.05276
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915323204075520
author Chu, Yucheng
He, Peng
Li, Hang
Han, Haoyu
Yang, Kaiqi
Xue, Yu
Li, Tingting
Krajcik, Joseph
Tang, Jiliang
author_facet Chu, Yucheng
He, Peng
Li, Hang
Han, Haoyu
Yang, Kaiqi
Xue, Yu
Li, Tingting
Krajcik, Joseph
Tang, Jiliang
contents Short answer assessment is a vital component of science education, allowing evaluation of students' complex three-dimensional understanding. Large language models (LLMs) that possess human-like ability in linguistic tasks are increasingly popular in assisting human graders to reduce their workload. However, LLMs' limitations in domain knowledge restrict their understanding in task-specific requirements and hinder their ability to achieve satisfactory performance. Retrieval-augmented generation (RAG) emerges as a promising solution by enabling LLMs to access relevant domain-specific knowledge during assessment. In this work, we propose an adaptive RAG framework for automated grading that dynamically retrieves and incorporates domain-specific knowledge based on the question and student answer context. Our approach combines semantic search and curated educational sources to retrieve valuable reference materials. Experimental results in a science education dataset demonstrate that our system achieves an improvement in grading accuracy compared to baseline LLM approaches. The findings suggest that RAG-enhanced grading systems can serve as reliable support with efficient performance gains.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05276
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation
Chu, Yucheng
He, Peng
Li, Hang
Han, Haoyu
Yang, Kaiqi
Xue, Yu
Li, Tingting
Krajcik, Joseph
Tang, Jiliang
Computation and Language
Short answer assessment is a vital component of science education, allowing evaluation of students' complex three-dimensional understanding. Large language models (LLMs) that possess human-like ability in linguistic tasks are increasingly popular in assisting human graders to reduce their workload. However, LLMs' limitations in domain knowledge restrict their understanding in task-specific requirements and hinder their ability to achieve satisfactory performance. Retrieval-augmented generation (RAG) emerges as a promising solution by enabling LLMs to access relevant domain-specific knowledge during assessment. In this work, we propose an adaptive RAG framework for automated grading that dynamically retrieves and incorporates domain-specific knowledge based on the question and student answer context. Our approach combines semantic search and curated educational sources to retrieve valuable reference materials. Experimental results in a science education dataset demonstrate that our system achieves an improvement in grading accuracy compared to baseline LLM approaches. The findings suggest that RAG-enhanced grading systems can serve as reliable support with efficient performance gains.
title Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2504.05276