Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yao, Yang, Li, Lingyu, Song, Jiaxin, Chen, Chiyu, He, Zhenqi, Wang, Yixu, Wang, Xin, Gu, Tianle, Li, Jie, Teng, Yan, Wang, Yingchun
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.14805
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918123619221504
author Yao, Yang
Li, Lingyu
Song, Jiaxin
Chen, Chiyu
He, Zhenqi
Wang, Yixu
Wang, Xin
Gu, Tianle
Li, Jie
Teng, Yan
Wang, Yingchun
author_facet Yao, Yang
Li, Lingyu
Song, Jiaxin
Chen, Chiyu
He, Zhenqi
Wang, Yixu
Wang, Xin
Gu, Tianle
Li, Jie
Teng, Yan
Wang, Yingchun
contents As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14805
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?
Yao, Yang
Li, Lingyu
Song, Jiaxin
Chen, Chiyu
He, Zhenqi
Wang, Yixu
Wang, Xin
Gu, Tianle
Li, Jie
Teng, Yan
Wang, Yingchun
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Multimedia
As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.
title Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Multimedia
url https://arxiv.org/abs/2506.14805