MDOI Convergence Chronicles 110.0901/CON.2026.00872
110.0901/CON.2026.00872
Article

Optimizing automated scoring in ILSAs with prompt compression

Ji Yoon Jung, Ummugul Bezirhan, Matthias von Davier 2025 Convergence Chronicles

Abstract

Automated scoring (AS) has become increasingly prevalent in educational measurement. However, applying it to international reading assessments remains challenging, particularly due to the length and complexity of the required prompting, driven by the need to include lengthy reading passages and detailed scoring guides. Processing these lengthy inputs results in high computational costs and may impede the performance of large language models (LLMs). This study explored the potential of optimizing AS with prompt compression using OpenAI's LLM, GPT-4o. Our results show that prompt compression significantly reduces the length of reading passages and scoring guides while maintaining their essential content. Reading passages and scoring guides were compressed to approximately 18% and 15% of their original lengths, respectively. Despite this substantial compression, the AS showed remarkable performance, with an accuracy of 92.87% and a kappa score of 0.8041, closely approximating the results obtained without compression. These findings suggest optimizing AS with prompt compression can improve its efficiency and scalability, particularly in international reading assessments.

Identifier Metadata

Identifier 110.0901/CON.2026.00872
Canonical mdoi:110.0901/CON.2026.00872
Resolver URL https://mdoi.org/110.0901/CON.2026.00872
Resource URL Open resource
Document URL Open document
Content Type Article
Authors Ji Yoon Jung, Ummugul Bezirhan, Matthias von Davier
Year 2025
Depositor Convergence Chronicles Organisation
Prefix 110.0901
Registered July 31, 2026
Updated July 31, 2026
Status Active
Visibility Public

Cite This Identifier

APA 7th Edition

Click to copy

MLA 9th Edition

Click to copy

Chicago 17th Edition

Click to copy

BibTeX

Click to copy

Persistent Identifier

mdoi:110.0901/CON.2026.00872

Click to copy

About MDOI

MDOI identifiers are permanent and unique identifiers assigned to digital objects to ensure long-term access, tracking, and referencing.

  • MDOI provides a permanent identity for digital objects.
  • Each MDOI is unique and points to one specific resource.
  • The prefix, such as 110.XXXX, identifies the registrant.
  • The suffix identifies the exact digital object.
  • MDOI remains stable even when a website URL changes.
  • It helps prevent broken links in digital publishing.
  • It makes academic and digital resources easier to find and cite.
  • MDOI supports proper tracking and management of digital content.
  • It improves the credibility and visibility of published resources.
  • MDOI ensures digital objects remain accessible, traceable, and reliable over time.
CO
Registered by Convergence Chronicles