Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.11220 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911379975307264 |
|---|---|
| author | Frade, Rafael Martins Panchendrarajan, Rrubaa Zubiaga, Arkaitz |
| author_facet | Frade, Rafael Martins Panchendrarajan, Rrubaa Zubiaga, Arkaitz |
| contents | Online disinformation poses an escalating threat to society, driven increasingly by the rapid spread of misleading content across both multimedia and multilingual platforms. While automated fact-checking methods have advanced in recent years, their effectiveness remains constrained by the scarcity of datasets that reflect these real-world complexities. To address this gap, we first present MultiCaption, a new dataset specifically designed for detecting contradictions in visual claims. Pairs of claims referring to the same image or video were labeled through multiple strategies to determine whether they contradict each other. The resulting dataset comprises 11,088 visual claims in 64 languages, offering a unique resource for building and evaluating misinformation-detection systems in truly multimodal and multilingual environments. We then provide comprehensive experiments using transformer-based architectures, natural language inference models, and large language models, establishing strong baselines for future research. The results show that MultiCaption is more challenging than standard NLI tasks, requiring task-specific finetuning for strong performance. Moreover, the gains from multilingual training and testing highlight the dataset's potential for building effective multilingual fact-checking pipelines without relying on machine translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11220 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MultiCaption: Detecting disinformation using multilingual visual claims Frade, Rafael Martins Panchendrarajan, Rrubaa Zubiaga, Arkaitz Computation and Language Online disinformation poses an escalating threat to society, driven increasingly by the rapid spread of misleading content across both multimedia and multilingual platforms. While automated fact-checking methods have advanced in recent years, their effectiveness remains constrained by the scarcity of datasets that reflect these real-world complexities. To address this gap, we first present MultiCaption, a new dataset specifically designed for detecting contradictions in visual claims. Pairs of claims referring to the same image or video were labeled through multiple strategies to determine whether they contradict each other. The resulting dataset comprises 11,088 visual claims in 64 languages, offering a unique resource for building and evaluating misinformation-detection systems in truly multimodal and multilingual environments. We then provide comprehensive experiments using transformer-based architectures, natural language inference models, and large language models, establishing strong baselines for future research. The results show that MultiCaption is more challenging than standard NLI tasks, requiring task-specific finetuning for strong performance. Moreover, the gains from multilingual training and testing highlight the dataset's potential for building effective multilingual fact-checking pipelines without relying on machine translation. |
| title | MultiCaption: Detecting disinformation using multilingual visual claims |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.11220 |