<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ravindran-choi-2025-investigating">
    <titleInfo>
        <title>Investigating Adversarial Robustness in LLM-based AES</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Renjith</namePart>
        <namePart type="family">Ravindran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ikkyu</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Joshua</namePart>
            <namePart type="family">Wilson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Ormerod</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Magdalen</namePart>
            <namePart type="family">Beiting Parrish</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>National Council on Measurement in Education (NCME)</publisher>
            <place>
                <placeTerm type="text">Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-218-84230-7</identifier>
    </relatedItem>
    <abstract>Automated Essay Scoring (AES) is one of the most widely studied applications of Natural Language Processing (NLP) in education and educational measurement. Recent advances with pre-trained Transformer-based large language models (LLMs) have shifted AES from feature-based modeling to leveraging contextualized language representations. These models provide rich semantic representations that substantially improve scoring accuracy and human–machine agreement compared to systems relying on handcrafted features. However, their robustness towards adversarially crafted inputs remains poorly understood. In this study, we define adversarial input as any modification of the essay text designed to fool an automated scoring system into assigning an inflated score. We evaluate a fine-tuned DeBERTa-based AES model on such inputs and show that it is highly susceptible to a simple text duplication attack, highlighting the need to consider adversarial robustness alongside accuracy in the development of AES systems.</abstract>
    <identifier type="citekey">ravindran-choi-2025-investigating</identifier>
    <location>
        <url>https://aclanthology.org/2025.aimecon-sessions.10/</url>
    </location>
    <part>
        <date>2025-10</date>
        <extent unit="page">
            <start>86</start>
            <end>91</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating Adversarial Robustness in LLM-based AES
%A Ravindran, Renjith
%A Choi, Ikkyu
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84230-7
%F ravindran-choi-2025-investigating
%X Automated Essay Scoring (AES) is one of the most widely studied applications of Natural Language Processing (NLP) in education and educational measurement. Recent advances with pre-trained Transformer-based large language models (LLMs) have shifted AES from feature-based modeling to leveraging contextualized language representations. These models provide rich semantic representations that substantially improve scoring accuracy and human–machine agreement compared to systems relying on handcrafted features. However, their robustness towards adversarially crafted inputs remains poorly understood. In this study, we define adversarial input as any modification of the essay text designed to fool an automated scoring system into assigning an inflated score. We evaluate a fine-tuned DeBERTa-based AES model on such inputs and show that it is highly susceptible to a simple text duplication attack, highlighting the need to consider adversarial robustness alongside accuracy in the development of AES systems.
%U https://aclanthology.org/2025.aimecon-sessions.10/
%P 86-91

Markdown (Informal)

[Investigating Adversarial Robustness in LLM-based AES](https://aclanthology.org/2025.aimecon-sessions.10/) (Ravindran & Choi, AIME-Con 2025)

• Investigating Adversarial Robustness in LLM-based AES (Ravindran & Choi, AIME-Con 2025)

ACL

• Renjith Ravindran and Ikkyu Choi. 2025. Investigating Adversarial Robustness in LLM-based AES. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 86–91, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).