The paper introduces MIDA, a multimodal benchmark that tests whether Multimodal Large Language Models can detect deception in multi‑party social interactions. It evaluates 12 state‑of‑the‑art MLLMs, finding that even powerful models like GPT‑4o perform poorly at distinguishing truthful from deceptive statements. The authors propose a Social Chain‑of‑Thought reasoning pipeline and a Dynamic Social Epistemic Memory module, showing that structured epistemic memory improves performance but that multimodal social‑cue reasoning remains a significant challenge.
arXiv:2606. 18988v1 Announce Type: new Abstract: Multimodal deception detection is critical for identifying fraudulent intentions, yet existing approaches predominantly rely on end to end black--box paradigms.
CoMMET is a new multimodal benchmark designed to evaluate Theory of Mind (ToM) in Multimodal Large Language Models (MLLMs). It expands beyond existing text-only, belief-focused tests by covering a wider range of mental states, incorporating moral evaluation, and enabling multi-turn, open-ended interactions. The dataset is grounded in psychological theory and provides a comprehensive assessment across different model families and sizes, revealing strengths, limitations, and future improvement directions.
arXiv:2608.22232v1 Announce Type: new Abstract: Real-world situation appearances can deviate from their underlying physical states, challenging the reliability of multimodal large language models (ML...
arXiv:2603. 23916v3 Announce Type: replace-cross Abstract: Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues for forensics and security.
Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoning is inherently multimodal, it remains largely unexplored by existing multimodal large language models (MLLMs).
PIVOTSBench is a benchmark designed to assess multimodal large language models’ ability to reason about fine‑grained interpersonal relationships. It is constructed from Social‑IQ 2.0 and YouTube data and evaluates models on predicting bidirectional relationship dimensions grounded in psychology research. The benchmark also includes auxiliary tasks that test models’ capacity to identify and use critical visual cues, and it examines the impact of visual modalities, social role information, and different prediction settings on model performance.
Theory of Mind (ToM), the ability to infer other's beliefs, intentions, and states of knowledge, is central to social interaction, yet remains challenging for current Multimodal Large Language Models (MLLMs), especially in multi-party meetings where cues are distributed across speech and behavior. Existing multimodal ToM benchmarks mainly focus on video-grounded question answering over overt, externally verifiable signals, and provide limited coverage of latent social states and group dynamics.
The paper introduces Multi-agent Undercover Gaming (MUG), a protocol that extends the Multi-Agent Debate (MAD) framework to address hallucinations in large language models. MUG reframes MAD as a detection task for ‘undercover’ agents—those that hallucinate—by using multimodal counterfactual tests that modify reference images to reveal hallucinations. The approach enhances factual verification, cross‑evidence reasoning, and active discussion among agents, aiming to improve reliability in multimodal reasoning.
arXiv:2605.27068v2 Announce Type: replace-cross Abstract: Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Mo...
The paper investigates whether multimodal large language models (MLLMs) can generate and detect realistic multimodal fake news on social media. Using a multi‑agent framework—comprising a story agent, an image agent, and a critic agent—the authors produced over 9,000 paired multimodal news posts across science, health, and entertainment domains. They benchmarked 16 open‑ and closed‑source MLLMs for automated detection and found that most models fall far short of human accuracy, especially in identifying image authenticity, highlighting the need for stronger defenses against social media fake news.
arXiv:2608. 03450v1 Announce Type: cross Abstract: Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction.
The paper introduces CAIT, a benchmark of 400 synthetic scenes featuring counter‑intuitive actions that challenge multimodal large language models (MLLMs). Human participants and proprietary models like Claude and Gemini perform well, but standard open‑source instruction‑tuned MLLMs fail, largely due to a strong language prior that overrides contradictory visual evidence. The study shows that Chain‑of‑Thought reasoning can help but introduces new issues, while targeted fine‑tuning and structured prompting can reduce reliance on language priors and improve visual grounding.