Exploration of Summarization by Generative Language Models for Automated Scoring of Long Essays

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hua, Haowei, Jiao, Hong, Wang, Xinyi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915626470080512
author Hua, Haowei
Jiao, Hong
Wang, Xinyi
author_facet Hua, Haowei
Jiao, Hong
Wang, Xinyi
contents BERT and its variants are extensively explored for automated scoring. However, a limit of 512 tokens for these encoder-based models showed the deficiency in automated scoring of long essays. Thus, this research explores generative language models for automated scoring of long essays via summarization and prompting. The results revealed great improvement of scoring accuracy with QWK increased from 0.822 to 0.8878 for the Learning Agency Lab Automated Essay Scoring 2.0 dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22830
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploration of Summarization by Generative Language Models for Automated Scoring of Long Essays
Hua, Haowei
Jiao, Hong
Wang, Xinyi
Computation and Language
Machine Learning
BERT and its variants are extensively explored for automated scoring. However, a limit of 512 tokens for these encoder-based models showed the deficiency in automated scoring of long essays. Thus, this research explores generative language models for automated scoring of long essays via summarization and prompting. The results revealed great improvement of scoring accuracy with QWK increased from 0.822 to 0.8878 for the Learning Agency Lab Automated Essay Scoring 2.0 dataset.
title Exploration of Summarization by Generative Language Models for Automated Scoring of Long Essays
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2510.22830