<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-trust">
    <titleInfo>
        <title>When Trust Meets Truth: Trust–Truth Separability in LLM-as-Judge</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xin</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuchen</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiahuan</namePart>
        <namePart type="family">Pei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Isao</namePart>
        <namePart type="family">Echizen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abdallah</namePart>
        <namePart type="family">El Ali</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saku</namePart>
        <namePart type="family">Sugawara</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>LLM-as-Judge systems can produce multi-field evaluations, such as trustworthiness, reliability, and factuality. These outputs are often interpreted as independent evidence. We test this assumption for a common pair of judgments: trust scoring and binary truth classification. On correctness-controlled QA, LLM judges align trust scores with truth verdicts more tightly than human behavioral reference, suggesting weaker separations between trust and truth judgment. We then apply stress tests by changing only source cues of identical QA between Human and AI, while holding QA content fixed. Source attribution shifts not only trust scores but also truth verdicts and logit-derived correct-side probabilities. Results show that current LLM-as-Judge protocols should not treat trust scores as independent evidence for truth judgments without testing their separability under trust-relevant perturbations.</abstract>
    <identifier type="citekey">sun-etal-2026-trust</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.389/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>8208</start>
            <end>8219</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Trust Meets Truth: Trust–Truth Separability in LLM-as-Judge
%A Sun, Xin
%A Wu, Di
%A Guo, Yuchen
%A Pei, Jiahuan
%A Echizen, Isao
%A El Ali, Abdallah
%A Sugawara, Saku
%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 sun-etal-2026-trust
%X LLM-as-Judge systems can produce multi-field evaluations, such as trustworthiness, reliability, and factuality. These outputs are often interpreted as independent evidence. We test this assumption for a common pair of judgments: trust scoring and binary truth classification. On correctness-controlled QA, LLM judges align trust scores with truth verdicts more tightly than human behavioral reference, suggesting weaker separations between trust and truth judgment. We then apply stress tests by changing only source cues of identical QA between Human and AI, while holding QA content fixed. Source attribution shifts not only trust scores but also truth verdicts and logit-derived correct-side probabilities. Results show that current LLM-as-Judge protocols should not treat trust scores as independent evidence for truth judgments without testing their separability under trust-relevant perturbations.
%U https://aclanthology.org/2026.findings-emnlp.389/
%P 8208-8219

Markdown (Informal)

[When Trust Meets Truth: Trust–Truth Separability in LLM-as-Judge](https://aclanthology.org/2026.findings-emnlp.389/) (Sun et al., Findings 2026)

• When Trust Meets Truth: Trust–Truth Separability in LLM-as-Judge (Sun et al., Findings 2026)

ACL

• Xin Sun, Di Wu, Yuchen Guo, Jiahuan Pei, Isao Echizen, Abdallah El Ali, and Saku Sugawara. 2026. When Trust Meets Truth: Trust–Truth Separability in LLM-as-Judge. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 8208–8219, Budapest, Hungary. Association for Computational Linguistics.