@inproceedings{wei-etal-2026-grafe,
title = "{GRAFE}: Graph-Reasoned Automated Feedback and Evaluation for Structure-Aware Essay Assessment",
author = "Wei, Hanyao and
Zhong, Jun and
Feng, Guang Cheng and
Kong, Li and
Tian, Xudong and
Zhou, Junsheng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1055/",
pages = "24211--24223",
ISBN = "979-8-89176-459-0",
abstract = "Automated Writing Evaluation has shifted from score-centered assessment toward revision-oriented feedback. However, current Large Language Models (LLMs) often generate generic comments that overlook essays' explicit structure and discourse-level flaws. We propose Graph-Reasoned Automated Feedback and Evaluation (GRAFE), which uses genre-specific structural graphs to guide score-feedback generation. GRAFE encodes discourse-level priors, including argumentation logic, evidence integration, and narrative progression, as continuous representations injected into the LLM. Furthermore, we introduce a training pipeline that combines two-stage Supervised Fine-Tuning for score-calibrated initialization with Group Relative Policy Optimization to align the model toward structural diagnostic accuracy, scoring consistency, and format compliance. We construct a graph-augmented ASAP++ feedback dataset with an expert-calibrated evaluation set. Experiments show that GRAFE outperforms text-only baselines on Structure-Aware Diagnosis and Structure-Grounded Actionability, demonstrating the value of explicit structural modeling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2026-grafe">
<titleInfo>
<title>GRAFE: Graph-Reasoned Automated Feedback and Evaluation for Structure-Aware Essay Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanyao</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guang</namePart>
<namePart type="given">Cheng</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junsheng</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Automated Writing Evaluation has shifted from score-centered assessment toward revision-oriented feedback. However, current Large Language Models (LLMs) often generate generic comments that overlook essays’ explicit structure and discourse-level flaws. We propose Graph-Reasoned Automated Feedback and Evaluation (GRAFE), which uses genre-specific structural graphs to guide score-feedback generation. GRAFE encodes discourse-level priors, including argumentation logic, evidence integration, and narrative progression, as continuous representations injected into the LLM. Furthermore, we introduce a training pipeline that combines two-stage Supervised Fine-Tuning for score-calibrated initialization with Group Relative Policy Optimization to align the model toward structural diagnostic accuracy, scoring consistency, and format compliance. We construct a graph-augmented ASAP++ feedback dataset with an expert-calibrated evaluation set. Experiments show that GRAFE outperforms text-only baselines on Structure-Aware Diagnosis and Structure-Grounded Actionability, demonstrating the value of explicit structural modeling.</abstract>
<identifier type="citekey">wei-etal-2026-grafe</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1055/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>24211</start>
<end>24223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GRAFE: Graph-Reasoned Automated Feedback and Evaluation for Structure-Aware Essay Assessment
%A Wei, Hanyao
%A Zhong, Jun
%A Feng, Guang Cheng
%A Kong, Li
%A Tian, Xudong
%A Zhou, Junsheng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wei-etal-2026-grafe
%X Automated Writing Evaluation has shifted from score-centered assessment toward revision-oriented feedback. However, current Large Language Models (LLMs) often generate generic comments that overlook essays’ explicit structure and discourse-level flaws. We propose Graph-Reasoned Automated Feedback and Evaluation (GRAFE), which uses genre-specific structural graphs to guide score-feedback generation. GRAFE encodes discourse-level priors, including argumentation logic, evidence integration, and narrative progression, as continuous representations injected into the LLM. Furthermore, we introduce a training pipeline that combines two-stage Supervised Fine-Tuning for score-calibrated initialization with Group Relative Policy Optimization to align the model toward structural diagnostic accuracy, scoring consistency, and format compliance. We construct a graph-augmented ASAP++ feedback dataset with an expert-calibrated evaluation set. Experiments show that GRAFE outperforms text-only baselines on Structure-Aware Diagnosis and Structure-Grounded Actionability, demonstrating the value of explicit structural modeling.
%U https://aclanthology.org/2026.emnlp-main.1055/
%P 24211-24223
Markdown (Informal)
[GRAFE: Graph-Reasoned Automated Feedback and Evaluation for Structure-Aware Essay Assessment](https://aclanthology.org/2026.emnlp-main.1055/) (Wei et al., EMNLP 2026)
ACL