GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs
Quick Take
GroupToM-Bench introduces the first multimodal benchmark for group-level Theory of Mind (ToM) in MLLMs, revealing significant gaps in current models' abilities to process social structures and non-linear dynamics. The framework includes a seven-level cognitive audit, highlighting the shortcomings in existing models compared to human baselines.
Key Points
- GroupToM-Bench benchmarks group-level ToM in multimodal large language models.
- Current MLLMs struggle with social structures and non-linear collective dynamics.
- The framework includes a seven-level cognitive audit for comprehensive evaluation.
- Experiments show a significant gap between model performance and human baselines.
Article Excerpt
From source RSS / original summaryarXiv:2606. 04184v1 Announce Type: new Abstract: True general intelligence requires not only a model of the physical world but also a social world model: the capacity to infer how individual mental states interact and crystallize into group-level outcomes. Despite notable progress in individual-level Theory of Mind (ToM) reasoning, existing multimodal large language models fail at this broader task.
Collective behavior emerges non-linearly from social tensions, conformity dynamics, and structural constraints, meaning it cannot be recovered by merely summing individual intentions. We present GroupToM-Bench, the first multimodal benchmark for group-level ToM, built around a causal chain spanning micro-level BDI states (belief, desire, intention), meso-level group tension and structural constraints, and macro-level outcome prediction and mechanistic attribution.
To probe this full arc, we develop a seven-level cognitive audit framework. Experiments reveal a gap between current models and human baselines, highlighting a failure to process social structures and non-linear collective dynamics.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Optimal Transport Flow Matching by Design
The study presents a novel approach to optimal transport (OT) flow matching, reformulating the problem by treating the prior as a design choice. This method achieves over 2x reduction in trajectory curvature compared to existing methods, improving generation quality in few-step regimes without altering the flow model. The approach integrates seamlessly with latent-space models and classifier-free guidance.