<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-zu-2025-exploring">
    <titleInfo>
        <title>Exploring the Interpretability of AI-Generated Response Detection with Probing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ikkyu</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiyun</namePart>
        <namePart type="family">Zu</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>Multiple strategies for AI-generated response detection have been proposed, with many high-performing ones built on language models. However, the decision-making processes of these detectors remain largely opaque. We addressed this knowledge gap by fine-tuning a language model for the detection task and applying probing techniques using adversarial examples. Our adversarial probing analysis revealed that the fine-tuned model relied heavily on a narrow set of lexical cues in making the classification decision. These findings underscore the importance of interpretability in AI-generated response detectors and highlight the value of adversarial probing as a tool for exploring model interpretability.</abstract>
    <identifier type="citekey">choi-zu-2025-exploring</identifier>
    <location>
        <url>https://aclanthology.org/2025.aimecon-sessions.12/</url>
    </location>
    <part>
        <date>2025-10</date>
        <extent unit="page">
            <start>99</start>
            <end>106</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploring the Interpretability of AI-Generated Response Detection with Probing
%A Choi, Ikkyu
%A Zu, Jiyun
%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 choi-zu-2025-exploring
%X Multiple strategies for AI-generated response detection have been proposed, with many high-performing ones built on language models. However, the decision-making processes of these detectors remain largely opaque. We addressed this knowledge gap by fine-tuning a language model for the detection task and applying probing techniques using adversarial examples. Our adversarial probing analysis revealed that the fine-tuned model relied heavily on a narrow set of lexical cues in making the classification decision. These findings underscore the importance of interpretability in AI-generated response detectors and highlight the value of adversarial probing as a tool for exploring model interpretability.
%U https://aclanthology.org/2025.aimecon-sessions.12/
%P 99-106

Markdown (Informal)

[Exploring the Interpretability of AI-Generated Response Detection with Probing](https://aclanthology.org/2025.aimecon-sessions.12/) (Choi & Zu, AIME-Con 2025)

• Exploring the Interpretability of AI-Generated Response Detection with Probing (Choi & Zu, AIME-Con 2025)

ACL

• Ikkyu Choi and Jiyun Zu. 2025. Exploring the Interpretability of AI-Generated Response Detection with Probing. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 99–106, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).