Skip to main navigation Skip to search Skip to main content

FusionASAG: An LLM-Enhanced Automatic Short Answer Grading Model for Subjective Questions in Online Education

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Subjective questions are crucial to assess students’ ability to analyze, synthesize, evaluate and create knowledge. In the massive online education scenarios, the manually scoring of subjective questions is time-consuming. Instead, it could be supported by the task of Short Answer Grading in Natural Language Process. However, it is worth noting that most existing automatic scoring system does not perform well on domain-specific and long questions. In this paper we address the challenges of automated short answer grading (ASAG) by proposing a novel scoring approach that strategically integrates a fine-tuned large language model (LLM), a neural network (NN) for feature extraction, and an answer-question relevance assessment module (RELEVANCE). Our method effectively scores student responses based on a set of predefined rubrics and reference answers. Our experiments on the ASAP-SAS dataset demonstrate that our method achieves an average Quadratic Weighted Kappa (QWK) score of 0.797, surpassing current state-of-the-art AutoSAS model, particularly excelling in longer tasks with a 11.9% improvement. Overall, our proposed method offers a robust solution for subjective question grading, ultimately contributing to more efficient educational assessment in a rapidly evolving learning environment.

Original languageEnglish
Title of host publicationComputer Science and Educational Informatization - 6th International Conference, CSEI 2024, Revised Selected Papers
EditorsKun Zhang, Xianhua Song, Mohammad S. Obaidat, Anas Bilal, Jun Hu, Zeguang Lu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages39-52
Number of pages14
ISBN (Print)9789819637348
DOIs
StatePublished - 2025
Event6th International Conference on Computer Science and Educational Informatization, CSEI 2024 - Haikou, China
Duration: 1 Nov 20243 Nov 2024

Publication series

NameCommunications in Computer and Information Science
Volume2447 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference6th International Conference on Computer Science and Educational Informatization, CSEI 2024
Country/TerritoryChina
CityHaikou
Period1/11/243/11/24

Keywords

  • Automatic Short Answer Grading
  • Generative Language Model
  • Model Fine-Tuning
  • Text Feature Extraction

Fingerprint

Dive into the research topics of 'FusionASAG: An LLM-Enhanced Automatic Short Answer Grading Model for Subjective Questions in Online Education'. Together they form a unique fingerprint.

Cite this