Saved in:
Bibliographic Details
Main Authors: Yang, Zixi, Li, Jiapeng, Diao, Muxi, Jing, Yinuo, Liang, Kongming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.08936
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915543448027136
author Yang, Zixi
Li, Jiapeng
Diao, Muxi
Jing, Yinuo
Liang, Kongming
author_facet Yang, Zixi
Li, Jiapeng
Diao, Muxi
Jing, Yinuo
Liang, Kongming
contents Recently, Multi-modal Large Language Models (MLLMs) have demonstrated significant performance across various video understanding tasks. However, their robustness, particularly when faced with manipulated video content, remains largely unexplored. In this paper, we introduce Ro-Bench, the first benchmark for evaluating MLLMs on dynamic out-of-distribution (OOD) counterfactual video test sets. Ro-Bench incorporates high-quality, diverse and temporally relevant video data, by editing Style, Object, Background and their compositions. We evaluated eight recent video MLLMs and found that current models exhibit substantial performance degradation on Ro-Bench when exposed to counterfactual video content. Furthermore, we demonstrate that fine-tuning MLLMs with counterfactual data enhances robustness, achieving a 21.73% performance increase on Ro-Bench and a 12.78% improvement across 20 tasks in the MVBench dataset. These findings underscore the effectiveness of counterfactual data in enhancing the video understanding ability of MLLMs. The code and data will be released shortly.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08936
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RO-Bench: Large-scale robustness evaluation of MLLMs with text-driven counterfactual videos
Yang, Zixi
Li, Jiapeng
Diao, Muxi
Jing, Yinuo
Liang, Kongming
Computer Vision and Pattern Recognition
Artificial Intelligence
Recently, Multi-modal Large Language Models (MLLMs) have demonstrated significant performance across various video understanding tasks. However, their robustness, particularly when faced with manipulated video content, remains largely unexplored. In this paper, we introduce Ro-Bench, the first benchmark for evaluating MLLMs on dynamic out-of-distribution (OOD) counterfactual video test sets. Ro-Bench incorporates high-quality, diverse and temporally relevant video data, by editing Style, Object, Background and their compositions. We evaluated eight recent video MLLMs and found that current models exhibit substantial performance degradation on Ro-Bench when exposed to counterfactual video content. Furthermore, we demonstrate that fine-tuning MLLMs with counterfactual data enhances robustness, achieving a 21.73% performance increase on Ro-Bench and a 12.78% improvement across 20 tasks in the MVBench dataset. These findings underscore the effectiveness of counterfactual data in enhancing the video understanding ability of MLLMs. The code and data will be released shortly.
title RO-Bench: Large-scale robustness evaluation of MLLMs with text-driven counterfactual videos
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.08936