<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-1">
    <titleInfo>
        <title>1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenkai</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liwen</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhenxiang</namePart>
        <namePart type="family">Guan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xuhui</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maarten</namePart>
        <namePart type="family">Sap</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the The First Workshop on LLM Security (LLMSEC)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Leon</namePart>
            <namePart type="family">Derczynski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jekaterina</namePart>
            <namePart type="family">Novikova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Muhao</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-279-4</identifier>
    </relatedItem>
    <abstract>Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources. Building on the theory of contextual integrity, we introduce a multi-agent framework that decomposes privacy reasoning into specialized subtasks—extraction, classification—reducing the information load on any single agent while enabling iterative validation and more reliable adherence to contextual privacy norms. Experiments on the ConfAIde benchmark with two LLMs (GPT-4, Llama3) demonstrate that our multi-agent system substantially reduces private information leakage (36% reduction) while maintaining the fidelity of public content compared to a single-agent system, showing the promise of multi-agent frameworks towards contextual privacy with LLMs.</abstract>
    <identifier type="citekey">li-etal-2025-1</identifier>
    <location>
        <url>https://aclanthology.org/2025.llmsec-1.9/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>115</start>
            <end>128</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning
%A Li, Wenkai
%A Sun, Liwen
%A Guan, Zhenxiang
%A Zhou, Xuhui
%A Sap, Maarten
%Y Derczynski, Leon
%Y Novikova, Jekaterina
%Y Chen, Muhao
%S Proceedings of the The First Workshop on LLM Security (LLMSEC)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-279-4
%F li-etal-2025-1
%X Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources. Building on the theory of contextual integrity, we introduce a multi-agent framework that decomposes privacy reasoning into specialized subtasks—extraction, classification—reducing the information load on any single agent while enabling iterative validation and more reliable adherence to contextual privacy norms. Experiments on the ConfAIde benchmark with two LLMs (GPT-4, Llama3) demonstrate that our multi-agent system substantially reduces private information leakage (36% reduction) while maintaining the fidelity of public content compared to a single-agent system, showing the promise of multi-agent frameworks towards contextual privacy with LLMs.
%U https://aclanthology.org/2025.llmsec-1.9/
%P 115-128

Markdown (Informal)

[1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning](https://aclanthology.org/2025.llmsec-1.9/) (Li et al., LLMSEC 2025)

• 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning (Li et al., LLMSEC 2025)

ACL

• Wenkai Li, Liwen Sun, Zhenxiang Guan, Xuhui Zhou, and Maarten Sap. 2025. 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning. In Proceedings of the The First Workshop on LLM Security (LLMSEC), pages 115–128, Vienna, Austria. Association for Computational Linguistics.