Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences - ACL Anthology

Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences

Xiyao Wang, Yuhang Zhou, Xiaoyu Liu, Hongjin Lu, Yuancheng Xu, Feihong He, Jaehong Yoon, Taixi Lu, Fuxiao Liu, Gedas Bertasius, Mohit Bansal, Huaxiu Yao, Furong Huang


Abstract
Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated. To address this challenge, this paper introduces Mementos, a new benchmark designed to assess MLLMs’ sequential image reasoning abilities. Mementos features 4,761 diverse image sequences with varying lengths. We also employ a GPT-4 assisted method to evaluate MLLM reasoning performance. Through a careful evaluation of nine recent MLLMs on Mementos, including GPT-4V and Gemini, we find that they struggle to accurately describe dynamic information about given image sequences, often leading to hallucinations/misrepresentations of objects and their corresponding behaviors. Our quantitative analysis and case studies identify three key factors impacting MLLMs’ sequential image reasoning: the correlation between object and behavioral hallucinations, the influence of co-occurring behaviors, and the compounding impact of behavioral hallucinations.
Anthology ID:
2024.acl-long.25
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
416–442
Language:
URL:
https://aclanthology.org/2024.acl-long.25
DOI:
10.18653/v1/2024.acl-long.25
Bibkey:
Cite (ACL):
Xiyao Wang, Yuhang Zhou, Xiaoyu Liu, Hongjin Lu, Yuancheng Xu, Feihong He, Jaehong Yoon, Taixi Lu, Fuxiao Liu, Gedas Bertasius, Mohit Bansal, Huaxiu Yao, and Furong Huang. 2024. Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 416–442, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences (Wang et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.25.pdf