You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with a Multi-Agent Conversations

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kirstein, Frederic, Khan, Muneeb, Wahle, Jan Philip, Ruas, Terry, Gipp, Bela
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912404061814784
author Kirstein, Frederic
Khan, Muneeb
Wahle, Jan Philip
Ruas, Terry
Gipp, Bela
author_facet Kirstein, Frederic
Khan, Muneeb
Wahle, Jan Philip
Ruas, Terry
Gipp, Bela
contents 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 in difficulty). These findings highlight that 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13001
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with a Multi-Agent Conversations
Kirstein, Frederic
Khan, Muneeb
Wahle, Jan Philip
Ruas, Terry
Gipp, Bela
Artificial Intelligence
Computation and Language
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 in difficulty). These findings highlight that 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.
title You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with a Multi-Agent Conversations
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2502.13001