Effectiveness of large language models in automated evaluation of argumentative essays: finetuning vs. zero-shot prompting

IF 6 1区文学 Q1 EDUCATION & EDUCATIONAL RESEARCH

Computer Assisted Language Learning Pub Date : 2024-07-01 DOI:10.1080/09588221.2024.2371395

Qiao Wang, John Maurice Gayed

引用次数: 0

Abstract

To address the long-standing challenge facing traditional automated writing evaluation (AWE) systems in assessing higher-order thinking, this study built an AWE system for scoring argumentative ess...

查看原文本刊更多论文

大语言模型在议论文自动评价中的有效性：微调与零点提示

为了解决传统的自动写作评估（AWE）系统在评估高阶思维方面面临的长期挑战，本研究建立了一个为议论文评分的AWE系统。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Computer Assisted Language Learning Multiple-

CiteScore

18.50

自引率

12.90%

发文量

期刊介绍： Computer Assisted Language Learning (CALL) is an intercontinental and interdisciplinary journal which leads the field in its dedication to all matters associated with the use of computers in language learning (L1 and L2), teaching and testing. It provides a forum to discuss the discoveries in the field and to exchange experience and information about existing techniques. The scope of the journal is intentionally wide-ranging and embraces a multitude of disciplines.