Papers by Runsheng Huang
MiRAGeNews: Multimodal Realistic AI-Generated News Detection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | inflammatory “fake” news content is increasingly common, but it is also difficult to detect by humans. |
| Approach: | They propose a dataset of 12,500 high-quality real and AI-generated image-caption pairs from state-of-the-art generators to combat the spread of fake news. |
| Outcome: | The proposed dataset improves on image-caption pairs from out-of-domain image generators and news publishers. |