MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929480247803904 |
|---|---|
| author | Jin, Yiqiao Choi, Minje Verma, Gaurav Wang, Jindong Kumar, Srijan |
| author_facet | Jin, Yiqiao Choi, Minje Verma, Gaurav Wang, Jindong Kumar, Srijan |
| contents | Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces. Multimodal Large Language Models (MLLMs) have emerged as a promising solution to these challenges, yet they struggle to accurately interpret human emotions and complex content such as misinformation. This paper introduces MM-Soc, a comprehensive benchmark designed to evaluate MLLMs' understanding of multimodal social media content. MM-Soc compiles prominent multimodal datasets and incorporates a novel large-scale YouTube tagging dataset, targeting a range of tasks from misinformation detection, hate speech detection, and social context generation. Through our exhaustive evaluation on ten size-variants of four open-source MLLMs, we have identified significant performance disparities, highlighting the need for advancements in models' social understanding capabilities. Our analysis reveals that, in a zero-shot setting, various types of MLLMs generally exhibit difficulties in handling social media tasks. However, MLLMs demonstrate performance improvements post fine-tuning, suggesting potential pathways for improvement. Our code and data are available at https://github.com/claws-lab/MMSoc.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14154 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms Jin, Yiqiao Choi, Minje Verma, Gaurav Wang, Jindong Kumar, Srijan Computation and Language Computer Vision and Pattern Recognition Computers and Society Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces. Multimodal Large Language Models (MLLMs) have emerged as a promising solution to these challenges, yet they struggle to accurately interpret human emotions and complex content such as misinformation. This paper introduces MM-Soc, a comprehensive benchmark designed to evaluate MLLMs' understanding of multimodal social media content. MM-Soc compiles prominent multimodal datasets and incorporates a novel large-scale YouTube tagging dataset, targeting a range of tasks from misinformation detection, hate speech detection, and social context generation. Through our exhaustive evaluation on ten size-variants of four open-source MLLMs, we have identified significant performance disparities, highlighting the need for advancements in models' social understanding capabilities. Our analysis reveals that, in a zero-shot setting, various types of MLLMs generally exhibit difficulties in handling social media tasks. However, MLLMs demonstrate performance improvements post fine-tuning, suggesting potential pathways for improvement. Our code and data are available at https://github.com/claws-lab/MMSoc.git. |
| title | MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms |
| topic | Computation and Language Computer Vision and Pattern Recognition Computers and Society |
| url | https://arxiv.org/abs/2402.14154 |