Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring
Heejin Do, Taehee Park, Sangwon Ryu, Gary Lee
Abstract
In automated essay scoring (AES), recent efforts have shifted toward cross-prompt settings that score essays on unseen prompts for practical applicability. However, prior methods trained with essay-score pairs of specific prompts pose challenges in obtaining prompt-generalized essay representation. In this work, we propose a grammar-aware cross-prompt trait scoring (GAPS), which internally captures prompt-independent syntactic aspects to learn generic essay representation. We acquire grammatical error-corrected information in essays via the grammar error correction technique and design the AES model to seamlessly integrate such information. By internally referring to both the corrected and the original essays, the model can focus on generic features during training. Empirical experiments validate our method’s generalizability, showing remarkable improvements in prompt-independent and grammar-related traits. Furthermore, GAPS achieves notable QWK gains in the most challenging cross-prompt scenario, highlighting its strength in evaluating unseen prompts.
BibTeX
@inproceedings{do-etal-2025-towards,
title = "Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring",
author = "Do, Heejin and
Park, Taehee and
Ryu, Sangwon and
Lee, Gary",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.153/",
pages = "2818--2824",
ISBN = "979-8-89176-195-7"
}