aiqbench analysis
This paper is primarily about AI: it introduces a benchmark (MIDA) that tests whether multimodal LLMs can detect deception in multi-party video and text, and proposes a reasoning pipeline and memory module to improve performance. The reported result is that even GPT-4o struggles, so the headline finding is a capability gap rather than a solved problem. For readers, the most useful takeaway is that the benchmark targets social cognition (modeling beliefs and intent), a area where current multimodal models remain weak and where evaluation standards are still immature.
Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions
arXiv:2511.16221v2 Announce Type: replace-cross Abstract: Despite their advanced reasoning capabilities, state-of-the-art Multimodal Large Language Models (MLLMs) still lack a core component of human intelligence: the ability to "read the room" and assess deception in complex social interactions. To rigorously evaluate this limitation, we introduce Multimodal Interactive Deception Assessment (MIDA), a new task and multimodal dataset comprising synchronized video and text with verifiable ground-truth labels for every statement. We benchmark 12 state-of-the-art open- and closed-source MLLMs and identify a substantial performance gap: even powerful models such as GPT-4o struggle to reliably distinguish truthful statements from deceptive ones. Our analysis shows that current models have difficulty grounding language in multimodal social cues and modeling what others know, believe, or intend. To address these limitations, we propose a Social Chain-of-Thought (SoCoT) reasoning pipeline and a Dynamic Social Epistemic Memory (DSEM) module. Experimental results show that structured epistemic memory consistently improves deception assessment, while multimodal social-cue reasoning remains a challenging and important direction for future research.
Title:Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions
Abstract:Despite their advanced reasoning capabilities, state-of-the-art Multimodal Large Language Models (MLLMs) still lack a core component of human intelligence: the ability to "read the room" and assess deception in complex social interactions. To rigorously evaluate this limitation, we introduce Multimodal Interactive Deception Assessment (MIDA), a new task and multimodal dataset comprising synchronized video and text with verifiable ground-truth labels for every statement. We benchmark 12 state-of-the-art open- and closed-source MLLMs and identify a substantial performance gap: even powerful models such as GPT-4o struggle to reliably distinguish truthful statements from deceptive ones. Our analysis shows that current models have difficulty grounding language in multimodal social cues and modeling what others know, believe, or intend. To address these limitations, we propose a Social Chain-of-Thought (SoCoT) reasoning pipeline and a Dynamic Social Epistemic Memory (DSEM) module. Experimental results show that structured epistemic memory consistently improves deception assessment, while multimodal social-cue reasoning remains a challenging and important direction for future research.
Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
arXiv:2511.16221 [cs.CV]
(or arXiv:2511.16221v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2511.16221 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 271 words
Related coverage
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
Latent Space · Sep 9, 2026
[AINews] AI Engineer NYC: Gemini 4 Argon, Vals AI Benchmarks
Latent Space · Oct 14, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026