MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings

This paper introduces a new way to evaluate how well AI models understand social interactions in group meetings. It highlights the challenges these models face in recognizing when people agree verbally but may actually disagree in their body language.

Analyze with PDFdigest

This video presentation explains the key concepts from the paper in plain language.

Content & Liability Disclaimer

This article and its accompanying video are automated summaries derived from the original research paper by Unknown authors. The original research was conducted solely by the paper's authors; PDFdigest did not conduct any of the research and makes no claims of ownership over the underlying scientific work.

The video narration is generated by artificial intelligence and references the paper's authors for attribution. The video is not narrated by any of the paper's authors. This content may contain inaccuracies, omissions, or misinterpretations of the original research. First-person language (e.g., "we found", "our results") reflects the original authors' voice, not PDFdigest's. Always read the original paper for accurate, verified information before making any decisions based on this content.

This content is provided "as is" without any warranties, express or implied. Simulated systems OÜ, its officers, directors, employees, and agents shall not be liable for any direct, indirect, incidental, special, consequential, or punitive damages arising from your use of, reliance on, or access to this content, including but not limited to errors, omissions, or misinterpretations of the original research. This disclaimer applies to the fullest extent permitted by applicable law.

Key Takeaways
  1. 1 Theory of Mind is crucial for understanding social interactions.
  2. 2 Current AI models struggle with interpreting complex social cues in meetings.
  3. 3 The MeetingToM benchmark helps assess AI's ability to understand hidden social dynamics.

Introduction

The introduction discusses the importance of Theory of Mind (ToM) in social interactions and the challenges faced by Multimodal Large Language Models (MLLMs) in understanding complex social states during multi-party meetings.

Example of Pseudo-Consensus

This section illustrates the concept of pseudo-consensus, where verbal agreement among participants may hide underlying dissent, emphasizing the need for models to recognize non-verbal cues and hidden attitudes.

Ours MeetingToM

MeetingToM is introduced as a benchmark designed to evaluate MLLMs’ capabilities in understanding complex social behaviors in meetings, focusing on subject-level, dyadic, and group-level reasoning.

How PDFdigest Helps You Understand Research

Instant Paper Analysis

Get structured summaries and key findings from dense PDFs in seconds.

Visual Explanations

Turn complex methods, figures, and results into clearer visual breakdowns.

AI-Powered Q&A

Ask focused questions and get answers grounded in the paper.

Try PDFdigest Free

Related Work

This section reviews existing research on social intelligence in meeting scenarios and multimodal social AI benchmarks, highlighting gaps that MeetingToM aims to address.

MeetingToM Benchmark

Details about the MeetingToM benchmark, its structure, and the evaluation protocol are provided, emphasizing its role in advancing the understanding of Theory of Mind in multimodal contexts.

Figures Explained

The paper’s visual material highlights the workflow and the main system components.

  • Figure 1: An example illustrating pseudo-consensus in a meeting scenario.. This figure demonstrates how verbal agreement can mask private dissent, highlighting the complexities of social interactions in meetings.

Limitations and Cautions

A useful limitation and caution is that this article summarizes the available paper text and extracted evidence; readers should consult the source paper before treating any interpretation as definitive.

The paper’s conclusions may depend on its source selection, definitions, assumptions, and the scope of its analysis, so follow-up reading is important.

PDFDIGEST AI

Struggling to understand complex research papers?

Upload any PDF and get instant AI-powered explanations, summaries, and visual breakdowns. Turn dense academic writing into clear, actionable insights.

Upload a Paper

Frequently Asked Questions

This paper introduces a new way to evaluate how well AI models understand social interactions in group meetings. It highlights the challenges these models face in recognizing when people agree verbally but may actually disagree in their body language.

The introduction discusses the importance of Theory of Mind (ToM) in social interactions and the challenges faced by Multimodal Large Language Models (MLLMs) in understanding complex social states during multi-party meetings.

Theory of Mind is crucial for understanding social interactions. Current AI models struggle with interpreting complex social cues in meetings. The MeetingToM benchmark helps assess AI’s ability to understand hidden social dynamics.

Yes. PDFDigest can turn this paper into a structured explanation, key takeaways, visual summaries, and a narrated video when available.

Related Research

Research

PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning

This paper presents a new method for improving how machines learn from visual information in reinforcement learning. The method adapts the way…

10 min read
Research

Enhancing Personalized Bladder Cancer Treatment Through Reinforcement Learning: A Recurrent Patient State-Transition Decision Support Framework

This paper discusses a new way to improve bladder cancer treatment using advanced computer techniques. It focuses on creating personalized treatment plans…

10 min read
Research

PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers

This paper presents a new method for improving how robots perform tasks that require precise contact with objects. The method, called PAC-ACT,…

10 min read