# MultiCaption: Detecting disinformation using multilingual visual claims

arXiv: https://arxiv.org/abs/2601.11220 · HTML: https://mlsanity.com/paper/2601.11220/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 69 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information](https://mlsanity.com/paper/2106.05707/) (2021)
- [NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media](https://mlsanity.com/paper/2104.05893/) (2021)
- [MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset](https://mlsanity.com/paper/2202.11684/) (2022)
- [GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features](https://mlsanity.com/paper/2207.09666/) (2022)
- [Multimodal Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2305.13507/) (2023)
- [VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias](https://mlsanity.com/paper/2304.14133/) (2023)
- [Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research](https://mlsanity.com/paper/2401.11969/) (2024)
- [Multilingual Previously Fact-Checked Claim Retrieval](https://mlsanity.com/paper/2305.07991/) (2023)
- [Factify 2: A Multimodal Fake News and Satire News Dataset](https://mlsanity.com/paper/2304.03897/) (2023)
- [Overview of the CLEF-2019 CheckThat!: Automatic Identification and Verification of Claims](https://mlsanity.com/paper/2109.15118/) (2021)
- [Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking](https://mlsanity.com/paper/2501.10860/) (2025)
- [MultiClaimNet: A Massively Multilingual Dataset of Fact-Checked Claim Clusters](https://mlsanity.com/paper/2503.22280/) (2025)
- [CLASH: A Benchmark for Cross-Modal Contradiction Detection](https://mlsanity.com/paper/2511.19199/) (2025)
- [SparseCL: Sparse Contrastive Learning for Contradiction Retrieval](https://mlsanity.com/paper/2406.10746/) (2024)

## Built on by (most cited first, 1 of 1)

- [Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems](https://mlsanity.com/paper/2601.21963/) (2026)

## Abstract (arXiv)

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.