<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-grace">
    <titleInfo>
        <title>GRACE: Generating Conflict-Aware Cases for Evaluating Policy Compliance in Enterprise Conversational AI</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinwon</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kyunghyun</namePart>
        <namePart type="family">Lim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gayeon</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sookeun</namePart>
        <namePart type="family">Yun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min-Oh</namePart>
        <namePart type="family">Heo</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 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yimu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yee</namePart>
            <namePart type="given">Man</namePart>
            <namePart type="family">Choi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Di</namePart>
            <namePart type="family">Wu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Siqi</namePart>
            <namePart type="family">Ouyang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mozhgan</namePart>
            <namePart type="given">Nasr</namePart>
            <namePart type="family">Azadani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yi</namePart>
            <namePart type="given">R</namePart>
            <namePart type="given">(May)</namePart>
            <namePart type="family">Fung</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">979-8-89176-478-1</identifier>
    </relatedItem>
    <abstract>Policy compliance in enterprise conversational AI is not binary: the same response can satisfy one stakeholder’s policy while violating another’s. Existing evaluations largely treat compliance as a single-policy problem, which makes cross-role conflict cases difficult to construct and assess. GRACE (Generating Conflict-Aware Cases for Evaluating Policy Compliance) addresses this gap by generating matched normal and conflict cases from the same underlying scenario, assigning role-wise expected verdicts through independent per-role policy evaluation, and scoring responses independently for each role rather than collapsing compliance into a single binary label. Across four domains, this process yields 1,109 labeled scenarios, including 309 cross-role conflicts. Evaluating five LLMs shows that deny cases are easiest, allow cases are depressed by over-refusal, and conflict cases are consistently hardest, revealing failures that single-label evaluation obscures. Per-persona analysis further shows that these errors are localized to specific domain-role combinations rather than uniform across models. GRACE therefore supports both policy review and deployment-time model selection.</abstract>
    <identifier type="citekey">kim-etal-2026-grace</identifier>
    <location>
        <url>https://aclanthology.org/2026.groundlm-1.59/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>796</start>
            <end>822</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GRACE: Generating Conflict-Aware Cases for Evaluating Policy Compliance in Enterprise Conversational AI
%A Kim, Jinwon
%A Lim, Kyunghyun
%A Kim, Gayeon
%A Yun, Sookeun
%A Heo, Min-Oh
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F kim-etal-2026-grace
%X Policy compliance in enterprise conversational AI is not binary: the same response can satisfy one stakeholder’s policy while violating another’s. Existing evaluations largely treat compliance as a single-policy problem, which makes cross-role conflict cases difficult to construct and assess. GRACE (Generating Conflict-Aware Cases for Evaluating Policy Compliance) addresses this gap by generating matched normal and conflict cases from the same underlying scenario, assigning role-wise expected verdicts through independent per-role policy evaluation, and scoring responses independently for each role rather than collapsing compliance into a single binary label. Across four domains, this process yields 1,109 labeled scenarios, including 309 cross-role conflicts. Evaluating five LLMs shows that deny cases are easiest, allow cases are depressed by over-refusal, and conflict cases are consistently hardest, revealing failures that single-label evaluation obscures. Per-persona analysis further shows that these errors are localized to specific domain-role combinations rather than uniform across models. GRACE therefore supports both policy review and deployment-time model selection.
%U https://aclanthology.org/2026.groundlm-1.59/
%P 796-822

Markdown (Informal)

[GRACE: Generating Conflict-Aware Cases for Evaluating Policy Compliance in Enterprise Conversational AI](https://aclanthology.org/2026.groundlm-1.59/) (Kim et al., GroundLM 2026)

• GRACE: Generating Conflict-Aware Cases for Evaluating Policy Compliance in Enterprise Conversational AI (Kim et al., GroundLM 2026)

ACL

• Jinwon Kim, Kyunghyun Lim, Gayeon Kim, Sookeun Yun, and Min-Oh Heo. 2026. GRACE: Generating Conflict-Aware Cases for Evaluating Policy Compliance in Enterprise Conversational AI. In Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026), pages 796–822, Budapest, Hungary. Association for Computational Linguistics.