<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kirstein-etal-2025-need">
    <titleInfo>
        <title>You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with Multi-Agent Conversations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Frederic</namePart>
        <namePart type="family">Kirstein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muneeb</namePart>
        <namePart type="family">Khan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="given">Philip</namePart>
        <namePart type="family">Wahle</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Terry</namePart>
        <namePart type="family">Ruas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bela</namePart>
        <namePart type="family">Gipp</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Meeting summarization suffers from limited high-quality data, mainly due to privacy restrictions and expensive collection processes. We address this gap with FAME, a dataset of 500 meetings in English and 300 in German produced by MIMIC, our new multi-agent meeting synthesis framework that generates meeting transcripts on a given knowledge source by defining psychologically grounded participant profiles, outlining the conversation, and orchestrating a large language model (LLM) debate. A modular post-processing step refines these outputs, mitigating potential repetitiveness and overly formal tones, ensuring coherent, credible dialogues at scale. We also propose a psychologically grounded evaluation framework assessing naturalness, social behavior authenticity, and transcript difficulties. Human assessments show that FAME approximates real-meeting spontaneity (4.5/5 in naturalness), preserves speaker-centric challenges (3/5 in spoken language), and introduces richer information-oriented difficulty (4/5 points in difficulty). These findings show FAME is a good and scalable proxy for real-world meeting conditions. It enables new test scenarios for meeting summarization research and other conversation-centric applications in tasks requiring conversation data or simulating social scenarios under behavioral constraints.</abstract>
    <identifier type="citekey">kirstein-etal-2025-need</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.599</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.599/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>11482</start>
            <end>11525</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with Multi-Agent Conversations
%A Kirstein, Frederic
%A Khan, Muneeb
%A Wahle, Jan Philip
%A Ruas, Terry
%A Gipp, Bela
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F kirstein-etal-2025-need
%X Meeting summarization suffers from limited high-quality data, mainly due to privacy restrictions and expensive collection processes. We address this gap with FAME, a dataset of 500 meetings in English and 300 in German produced by MIMIC, our new multi-agent meeting synthesis framework that generates meeting transcripts on a given knowledge source by defining psychologically grounded participant profiles, outlining the conversation, and orchestrating a large language model (LLM) debate. A modular post-processing step refines these outputs, mitigating potential repetitiveness and overly formal tones, ensuring coherent, credible dialogues at scale. We also propose a psychologically grounded evaluation framework assessing naturalness, social behavior authenticity, and transcript difficulties. Human assessments show that FAME approximates real-meeting spontaneity (4.5/5 in naturalness), preserves speaker-centric challenges (3/5 in spoken language), and introduces richer information-oriented difficulty (4/5 points in difficulty). These findings show FAME is a good and scalable proxy for real-world meeting conditions. It enables new test scenarios for meeting summarization research and other conversation-centric applications in tasks requiring conversation data or simulating social scenarios under behavioral constraints.
%R 10.18653/v1/2025.findings-acl.599
%U https://aclanthology.org/2025.findings-acl.599/
%U https://doi.org/10.18653/v1/2025.findings-acl.599
%P 11482-11525

Markdown (Informal)

[You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with Multi-Agent Conversations](https://aclanthology.org/2025.findings-acl.599/) (Kirstein et al., Findings 2025)

• You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with Multi-Agent Conversations (Kirstein et al., Findings 2025)

ACL

• Frederic Kirstein, Muneeb Khan, Jan Philip Wahle, Terry Ruas, and Bela Gipp. 2025. You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with Multi-Agent Conversations. In Findings of the Association for Computational Linguistics: ACL 2025, pages 11482–11525, Vienna, Austria. Association for Computational Linguistics.