Harnessing LLMs for multi-dimensional writing assessment: Reliability and alignment with human judgments

Date:2026-09-06 clicks:

Impact Factor:3.4

DOI number:10.1016/j.heliyon.2024.e34262

Affiliation of Author(s):北京科技大学外国语学院

Teaching and Research Group:研究生英语系

Journal:Heliyon

Key Words:large language models; writing assessment; reliability; human judgments

Note:作者顺序：Xiaoyi Tang, Hongwei Chen, Daoyu Lin, Kexin Li；正式发布日期：2024-07-30。

Document Code:e34262

Volume:10

Issue:14

Page Number:e34262

Translation or Not:no

Included Journals:SCI

Links to published journals:https://doi.org/10.1016/j.heliyon.2024.e34262

Pre One:Incorporating Fine-Grained Linguistic Features and Explainable AI into Multi-Dimensional Automated Writing Assessment Next One:Book Review: Dennis Tay, Data Analytics for Discourse Analysis with Python: The Case of Therapy Talk