@inproceedings{labib-etal-2026-wraft,
title = "{W}r{AFT}: A Modularized Automated Writing Evaluation System for {L}2 Argumentative Essays",
author = "Labib, Adnan and
Huang, Yixuan and
Wu, Jiahui and
Gayed, John Maurice and
Yuan, Zheng and
Wang, Qiao",
editor = "Wang, Xiaoman and
Wang, Qianyu and
Liu, Zhengyuan and
Chen, Nancy F. and
Yuan, Zheng and
Lan, Yunshi and
Jiang, Jing",
booktitle = "Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.multilll-1.1/",
pages = "1--18",
ISBN = "979-8-89176-449-1",
abstract = "Second language writers rarely receive the detailed feedback they need to improve, as comprehensive feedback takes teachers days per class. To solve this, we present WrAFT, a Writing Assessment and Feedback Tool, that delivers reliable scores along with effective comprehensive feedback for argumentative essays. WrAFT adopts a modular design by dividing the automated writing evaluation (AWE) into essay scoring, surface-level feedback and deep-level feedback. In building the system, various Large Language Models (LLMs) have been evaluated, including LLaMA-3.3-70B-Instruct, GPT-4o, and Claude 3.7, through both supervised fine-tuning and direct prompting. Evaluation shows that WrAFT achieves state-of-the-art performance in scoring with a Quadratic Weighted Kappa (QWK) of 0.84 on a proprietary dataset of 480 TOEFL Independent Writing essays. More importantly, human evaluation of system-generated feedback also reveals high approval ratings (96.14{\%} for surface-level, 93.03{\%} for deep-level macro feedback, and 94.69{\%} for deep-level micro feedback). Publicly available interactive user interface has also been developed for the system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="labib-etal-2026-wraft">
<titleInfo>
<title>WrAFT: A Modularized Automated Writing Evaluation System for L2 Argumentative Essays</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adnan</namePart>
<namePart type="family">Labib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahui</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">Maurice</namePart>
<namePart type="family">Gayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoman</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunshi</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-449-1</identifier>
</relatedItem>
<abstract>Second language writers rarely receive the detailed feedback they need to improve, as comprehensive feedback takes teachers days per class. To solve this, we present WrAFT, a Writing Assessment and Feedback Tool, that delivers reliable scores along with effective comprehensive feedback for argumentative essays. WrAFT adopts a modular design by dividing the automated writing evaluation (AWE) into essay scoring, surface-level feedback and deep-level feedback. In building the system, various Large Language Models (LLMs) have been evaluated, including LLaMA-3.3-70B-Instruct, GPT-4o, and Claude 3.7, through both supervised fine-tuning and direct prompting. Evaluation shows that WrAFT achieves state-of-the-art performance in scoring with a Quadratic Weighted Kappa (QWK) of 0.84 on a proprietary dataset of 480 TOEFL Independent Writing essays. More importantly, human evaluation of system-generated feedback also reveals high approval ratings (96.14% for surface-level, 93.03% for deep-level macro feedback, and 94.69% for deep-level micro feedback). Publicly available interactive user interface has also been developed for the system.</abstract>
<identifier type="citekey">labib-etal-2026-wraft</identifier>
<location>
<url>https://aclanthology.org/2026.multilll-1.1/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WrAFT: A Modularized Automated Writing Evaluation System for L2 Argumentative Essays
%A Labib, Adnan
%A Huang, Yixuan
%A Wu, Jiahui
%A Gayed, John Maurice
%A Yuan, Zheng
%A Wang, Qiao
%Y Wang, Xiaoman
%Y Wang, Qianyu
%Y Liu, Zhengyuan
%Y Chen, Nancy F.
%Y Yuan, Zheng
%Y Lan, Yunshi
%Y Jiang, Jing
%S Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-449-1
%F labib-etal-2026-wraft
%X Second language writers rarely receive the detailed feedback they need to improve, as comprehensive feedback takes teachers days per class. To solve this, we present WrAFT, a Writing Assessment and Feedback Tool, that delivers reliable scores along with effective comprehensive feedback for argumentative essays. WrAFT adopts a modular design by dividing the automated writing evaluation (AWE) into essay scoring, surface-level feedback and deep-level feedback. In building the system, various Large Language Models (LLMs) have been evaluated, including LLaMA-3.3-70B-Instruct, GPT-4o, and Claude 3.7, through both supervised fine-tuning and direct prompting. Evaluation shows that WrAFT achieves state-of-the-art performance in scoring with a Quadratic Weighted Kappa (QWK) of 0.84 on a proprietary dataset of 480 TOEFL Independent Writing essays. More importantly, human evaluation of system-generated feedback also reveals high approval ratings (96.14% for surface-level, 93.03% for deep-level macro feedback, and 94.69% for deep-level micro feedback). Publicly available interactive user interface has also been developed for the system.
%U https://aclanthology.org/2026.multilll-1.1/
%P 1-18
Markdown (Informal)
[WrAFT: A Modularized Automated Writing Evaluation System for L2 Argumentative Essays](https://aclanthology.org/2026.multilll-1.1/) (Labib et al., Multi-LLL 2026)
ACL