# NepOOC-M: Bilingual Nepali-English Benchmark and Comparative Analysis of Multimodal Architectures for OOC Detection

arXiv: https://arxiv.org/abs/2608.19212 · HTML: https://mlsanity.com/paper/2608.19212/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 18 Jun 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media](https://mlsanity.com/paper/2104.05893/) (2021)
- [SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2403.03170/) (2024)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset](https://mlsanity.com/paper/2202.11684/) (2022)
- [Improving Fake News Detection by Using an Entity-enhanced Framework to Fuse Diverse Multimodal Clues](https://mlsanity.com/paper/2108.10509/) (2021)
- [VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias](https://mlsanity.com/paper/2304.14133/) (2023)
- [Multimodal Misinformation Detection using Large Vision-Language Models](https://mlsanity.com/paper/2407.14321/) (2024)
- [RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection](https://mlsanity.com/paper/2311.09939/) (2023)
- [COVE: COntext and VEracity prediction for out-of-context images](https://mlsanity.com/paper/2502.01194/) (2025)
- [Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model](https://mlsanity.com/paper/2304.07633/) (2023)
- [Evidence-Grounded Multimodal Misinformation Detection with Attention-Based GNNs](https://mlsanity.com/paper/2505.18221/) (2025)
- [GRaMuFeN: Graph-based Multi-modal Fake News Detection in Social Media](https://mlsanity.com/paper/2310.07668/) (2023)

## Abstract (arXiv)

Out-of-context (OOC) misinformation pairs authentic images with misleading captions to construct false narratives without image manipulation, making detection a problem of multimodal alignment rather than image forensics. Despite the prevalence and consequences of OOC misinformation in Nepal, no public benchmark exists for Nepali. We introduce NepOOC, the first publicly available Nepali-dominant multilingual OOC benchmark, comprising 1,090 image-caption pairs (545 pristine, 545 OOC) annotated across five typologies (fabricated, miscaptioned, temporal mismatch, geographic mismatch, identity mismatch) with inter-annotator agreement kappa = 0.84. Systematic evaluation of five multimodal architectures alongside text-only and image-only baselines reveals that caption semantics appear sufficient for strong performance at the current dataset scale. A text-only mBERT model achieves 94.65+/-0.20% Macro-F1, statistically equivalent to the best multimodal system (ResNet-50+mBERT, 94.65+/-0.20%; McNemar median p = 1.000, 0/5 seeds significant at alpha = 0.05). Image-only models perform near chance (33-50%), while training-size scaling suggests that dataset expansion is a more direct path to progress than architectural sophistication or regional specialisation.