Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.13607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929374058512384 |
|---|---|
| author | Luo, Fuwen Chen, Chi Wan, Zihao Kang, Zhaolu Yan, Qidong Li, Yingjie Wang, Xiaolong Wang, Siyu Wang, Ziyue Mi, Xiaoyue Li, Peng Ma, Ning Sun, Maosong Liu, Yang |
| author_facet | Luo, Fuwen Chen, Chi Wan, Zihao Kang, Zhaolu Yan, Qidong Li, Yingjie Wang, Xiaolong Wang, Siyu Wang, Ziyue Mi, Xiaoyue Li, Peng Ma, Ning Sun, Maosong Liu, Yang |
| contents | Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of their capabilities has grown increasingly important. However, most existing benchmarks fail to consider that, in certain situations, images need to be interpreted within a broader context. In this work, we introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. Further analysis confirms that these models struggle to effectively extract and utilize contextual information to improve their understanding of images. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner. View our project website at https://thunlp-mt.github.io/CODIS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13607 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models Luo, Fuwen Chen, Chi Wan, Zihao Kang, Zhaolu Yan, Qidong Li, Yingjie Wang, Xiaolong Wang, Siyu Wang, Ziyue Mi, Xiaoyue Li, Peng Ma, Ning Sun, Maosong Liu, Yang Computer Vision and Pattern Recognition Computation and Language Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of their capabilities has grown increasingly important. However, most existing benchmarks fail to consider that, in certain situations, images need to be interpreted within a broader context. In this work, we introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. Further analysis confirms that these models struggle to effectively extract and utilize contextual information to improve their understanding of images. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner. View our project website at https://thunlp-mt.github.io/CODIS. |
| title | CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2402.13607 |