Abstract
The proliferation of inflammatory or misleading “fake” news content has become increasingly common in recent years. Simultaneously, it has become easier than ever to use AI tools to generate photorealistic images depicting any scene imaginable. Combining these two—AI-generated fake news content—is particularly potent and dangerous. To combat the spread of AI-generated fake news, we propose the MiRAGeNews Dataset, a dataset of 12,500 high-quality real and AI-generated image-caption pairs from state-of-the-art generators. We find that our dataset poses a significant challenge to humans (60% F-1) and state-of-the-art multi-modal LLMs (< 24% F-1). Using our dataset we train a multi-modal detector (MiRAGe) that improves by +5.1% F-1 over state-of-the-art baselines on image-caption pairs from out-of-domain image generators and news publishers. We release our code and data to aid future work on detecting AI-generated content.- Anthology ID:
- 2024.findings-emnlp.959
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 16436–16448
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.959
- DOI:
- 10.18653/v1/2024.findings-emnlp.959
- Cite (ACL):
- Runsheng Huang, Liam Dugan, Yue Yang, and Chris Callison-Burch. 2024. MiRAGeNews: Multimodal Realistic AI-Generated News Detection. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16436–16448, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- MiRAGeNews: Multimodal Realistic AI-Generated News Detection (Huang et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.959.pdf