AICLFeb 18, 2025

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

arXiv:2502.13001v21 citationsh-index: 14ACL
Originality Incremental advance
AI Analysis

This provides a scalable proxy for real-world meeting conditions, enabling new test scenarios for meeting summarization and conversation-centric applications, though it is incremental in synthesizing data rather than solving the underlying privacy or collection issues.

The paper tackles the scarcity of high-quality meeting transcripts for summarization by introducing FAME, a dataset of 800 meetings generated using the MIMIC multi-agent synthesis framework, which achieves high naturalness scores (4.5/5) and introduces richer information-oriented difficulty (4/5).

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes