<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-ai">
    <titleInfo>
        <title>When AI-Text Detectors Become Evidence: Rethinking Detection for Human Decisions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiatao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mao</namePart>
        <namePart type="family">Ye</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinyu</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cheng</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xunjian</namePart>
        <namePart type="family">Yin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaojun</namePart>
        <namePart type="family">Wan</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>AI-generated-text detectors are evaluated as classifiers, yet consequential deployments use detector outputs as evidence that people inspect, trust, contest, or use to escalate decisions. We call this mismatch the classification–evidence gap. The gap makes scalar detector scores a weak deployment interface: they hide the basis of a judgment, invite overtrust, and can turn false positives into accusations. We argue that AI-text detection should be evaluated as evidence-grounded decision support rather than as authorship proof. We introduce AGENT-XTrust, a guideline-expert detector that returns direct MetaAgent labels without target-domain scalar-cutoff calibration and converts each document-level judgment into inspectable evidence records containing local labels, rationales, confidence estimates, and linked spans. Across three domains and four generators, AGENT-XTrust preserves strong binary accuracy while producing inspectable, contestable evidence. In a controlled fixed-stimulus user study, participants assigned to the full AGENT-XTrust system-and-interface package achieved 19.8 and 11.3 points higher decision accuracy than those assigned to the score-only and score-plus-explanation packages, respectively; overtrust on each condition’s detector-wrong cases was 17.8 and 18.3 points lower. These results suggest a broader evaluation target for AI-text detection: not only whether a detector is correct, but whether complete detector-and-evidence packages support reliable human decisions under uncertainty.</abstract>
    <identifier type="citekey">li-etal-2026-ai</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1539/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>32727</start>
            <end>32757</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When AI-Text Detectors Become Evidence: Rethinking Detection for Human Decisions
%A Li, Jiatao
%A Ye, Mao
%A Hu, Xinyu
%A Peng, Cheng
%A Yin, Xunjian
%A Wan, Xiaojun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F li-etal-2026-ai
%X AI-generated-text detectors are evaluated as classifiers, yet consequential deployments use detector outputs as evidence that people inspect, trust, contest, or use to escalate decisions. We call this mismatch the classification–evidence gap. The gap makes scalar detector scores a weak deployment interface: they hide the basis of a judgment, invite overtrust, and can turn false positives into accusations. We argue that AI-text detection should be evaluated as evidence-grounded decision support rather than as authorship proof. We introduce AGENT-XTrust, a guideline-expert detector that returns direct MetaAgent labels without target-domain scalar-cutoff calibration and converts each document-level judgment into inspectable evidence records containing local labels, rationales, confidence estimates, and linked spans. Across three domains and four generators, AGENT-XTrust preserves strong binary accuracy while producing inspectable, contestable evidence. In a controlled fixed-stimulus user study, participants assigned to the full AGENT-XTrust system-and-interface package achieved 19.8 and 11.3 points higher decision accuracy than those assigned to the score-only and score-plus-explanation packages, respectively; overtrust on each condition’s detector-wrong cases was 17.8 and 18.3 points lower. These results suggest a broader evaluation target for AI-text detection: not only whether a detector is correct, but whether complete detector-and-evidence packages support reliable human decisions under uncertainty.
%U https://aclanthology.org/2026.findings-emnlp.1539/
%P 32727-32757

Markdown (Informal)

[When AI-Text Detectors Become Evidence: Rethinking Detection for Human Decisions](https://aclanthology.org/2026.findings-emnlp.1539/) (Li et al., Findings 2026)

• When AI-Text Detectors Become Evidence: Rethinking Detection for Human Decisions (Li et al., Findings 2026)

ACL

• Jiatao Li, Mao Ye, Xinyu Hu, Cheng Peng, Xunjian Yin, and Xiaojun Wan. 2026. When AI-Text Detectors Become Evidence: Rethinking Detection for Human Decisions. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 32727–32757, Budapest, Hungary. Association for Computational Linguistics.