Mohammad Nadeem
Are Foundation Models the Next-Generation Social Media Content Moderators?
Nadeem, Mohammad; Javed, Laeeba; Sohail, Shahab Saquib; Cambria, Erik; Hussain, Amir
Authors
Abstract
Recent progress in artificial intelligence (AI) tools and systems has been significant, especially in their reasoning and efficiency. Notable examples include generative AI-based large language models (LLMs) like Generative Pre-trained Transformer 3.5 (GPT-3.5), GPT-4, and Gemini, among others. In our work, we evaluated the effectiveness of fine-tuned deep learning models compared to general-purpose LLMs in moderating image-based content. We used deep learning models such as convolutional neural networks, ResNet50, and VGG-16, trained them for violence detection on an image dataset, and tested them on a separate dataset. The same test dataset was also evaluated using Large Language and Vision Assistant (LLaVa) and GPT-4, two LLMs that can process images. The results demonstrate that VGG-16 model had the highest accuracy at 0.94, while LLaVa had the lowest at 0.66. GPT-4 showed superiority over LLaVa with an accuracy value of 0.9242. LLaVa recorded the highest precision of all models.
Citation
Nadeem, M., Javed, L., Sohail, S. S., Cambria, E., & Hussain, A. (2024). Are Foundation Models the Next-Generation Social Media Content Moderators?. IEEE Intelligent Systems, 39(6), 70-80. https://doi.org/10.1109/mis.2024.3477109
Journal Article Type | Article |
---|---|
Online Publication Date | Dec 5, 2024 |
Publication Date | 2024-11 |
Deposit Date | Dec 17, 2024 |
Publicly Available Date | Dec 17, 2024 |
Journal | IEEE Intelligent Systems |
Print ISSN | 1541-1672 |
Publisher | Institute of Electrical and Electronics Engineers |
Peer Reviewed | Peer Reviewed |
Volume | 39 |
Issue | 6 |
Pages | 70-80 |
DOI | https://doi.org/10.1109/mis.2024.3477109 |
Files
Are Foundation Models the Next-Generation Social Media Content Moderators? (accepted version)
(1.4 Mb)
PDF
You might also like
MA-Net: Resource-efficient multi-attentional network for end-to-end speech enhancement
(2024)
Journal Article
Artificial intelligence enabled smart mask for speech recognition for future hearing devices
(2024)
Journal Article
An Attention‐Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification
(2024)
Journal Article