Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Liangliang, Xie, Huiru, Qin, Zhihao, Guo, Yiming, Rohde, Jacqueline, Zhang, Ying
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911282727223296
author Chen, Liangliang
Xie, Huiru
Qin, Zhihao
Guo, Yiming
Rohde, Jacqueline
Zhang, Ying
author_facet Chen, Liangliang
Xie, Huiru
Qin, Zhihao
Guo, Yiming
Rohde, Jacqueline
Zhang, Ying
contents This research full paper presents an enhancement pipeline for large language models (LLMs) in assessing homework for an undergraduate circuit analysis course, aiming to improve LLMs' capacity to provide personalized support to electrical engineering students. Existing evaluations have demonstrated that GPT-4o possesses promising capabilities in assessing student homework in this domain. Building on these findings, we enhance GPT-4o's performance through multi-step prompting, contextual data augmentation, and the incorporation of targeted hints. These strategies effectively address common errors observed in GPT-4o's responses when using simple prompts, leading to a substantial improvement in assessment accuracy. Specifically, the correct response rate for GPT-4o increases from 74.71% to 97.70% after applying the enhanced prompting and augmented data on entry-level circuit analysis topics. This work lays a foundation for the effective integration of LLMs into circuit analysis instruction and, more broadly, into engineering education.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis
Chen, Liangliang
Xie, Huiru
Qin, Zhihao
Guo, Yiming
Rohde, Jacqueline
Zhang, Ying
Computers and Society
Artificial Intelligence
Human-Computer Interaction
This research full paper presents an enhancement pipeline for large language models (LLMs) in assessing homework for an undergraduate circuit analysis course, aiming to improve LLMs' capacity to provide personalized support to electrical engineering students. Existing evaluations have demonstrated that GPT-4o possesses promising capabilities in assessing student homework in this domain. Building on these findings, we enhance GPT-4o's performance through multi-step prompting, contextual data augmentation, and the incorporation of targeted hints. These strategies effectively address common errors observed in GPT-4o's responses when using simple prompts, leading to a substantial improvement in assessment accuracy. Specifically, the correct response rate for GPT-4o increases from 74.71% to 97.70% after applying the enhanced prompting and augmented data on entry-level circuit analysis topics. This work lays a foundation for the effective integration of LLMs into circuit analysis instruction and, more broadly, into engineering education.
title Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis
topic Computers and Society
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2511.18221