aiqbench analysis
This study provides a rigorous psychophysical analysis comparing human visual search capabilities with those of Multimodal Large Language Models (MLLMs). While MLLMs demonstrate strong correlations in error rates and replicate high-level performance signatures, they exhibit distinct computational biases regarding target-absent trials that differ from human cognitive strategies. The findings highlight both the convergence of model behavior with human cognition and the fundamental divergence in underlying processing mechanisms for complex visual tasks.
Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs
arXiv:2610.05463v1 Announce Type: cross Abstract: Visual search is a fundamental cognitive ability. This study investigates whether Multimodal Large Language Models (MLLMs) exhibit human-like difficulty signatures in visual search tasks. We compared search performance of humans (n = 1,250) and MLLMs using identical 2D and 3D stimuli across different set sizes. Both groups showed efficient performance in feature searches, most clearly when the target had a unique color, but performance degradation in conjunction searches as set sizes increased. Additionally, we found strong correlations between human and MLLM error rates ($\rho = 0.82$), which suggests that MLLMs are sensitive to similar objective complexities, such as stimulus heterogeneity. However, differences were found as well: whereas humans invested extra search time to respond accurately on target-absent trials, MLLMs exhibited extreme present/absent response biases in complex searches. We conclude that MLLMs replicate high-level human performance signatures, yet their underlying computations differ significantly.
Title:Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs
Abstract:Visual search is a fundamental cognitive ability. This study investigates whether Multimodal Large Language Models (MLLMs) exhibit human-like difficulty signatures in visual search tasks. We compared search performance of humans (n = 1,250) and MLLMs using identical 2D and 3D stimuli across different set sizes. Both groups showed efficient performance in feature searches, most clearly when the target had a unique color, but performance degradation in conjunction searches as set sizes increased. Additionally, we found strong correlations between human and MLLM error rates ($\rho = 0.82$), which suggests that MLLMs are sensitive to similar objective complexities, such as stimulus heterogeneity. However, differences were found as well: whereas humans invested extra search time to respond accurately on target-absent trials, MLLMs exhibited extreme present/absent response biases in complex searches. We conclude that MLLMs replicate high-level human performance signatures, yet their underlying computations differ significantly.
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2610.05463 [cs.HC]
(or arXiv:2610.05463v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2610.05463 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1007/s42113-026-00333-4 Focus to learn more DOI(s) linking to related resources
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 · 267 words
