Saved in:
Bibliographic Details
Main Authors: Kishore, Aditya, Kumar, Gaurav, Patro, Jasabanta
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.05097
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912819167887360
author Kishore, Aditya
Kumar, Gaurav
Patro, Jasabanta
author_facet Kishore, Aditya
Kumar, Gaurav
Patro, Jasabanta
contents Misinformation on the web increasingly appears in multimodal forms, combining text, images, and OCR-rendered content in ways that amplify harm to public trust and vulnerable communities. While prior fact-checking systems often rely on unimodal signals or shallow fusion strategies, modern misinformation campaigns operate across modalities and require models that can reason over subtle cross-modal inconsistencies in a transparent and responsible manner. We introduce MultiCheck, a lightweight and interpretable framework for multimodal fact verification that jointly analyzes textual, visual, and OCR evidence. At its core, MultiCheck employs a relational fusion module based on element-wise difference and product operations, allowing for explicit cross-modal interaction modeling with minimal computational overhead. A contrastive alignment objective further helps the model distinguish between supporting and refuting evidence while maintaining a small memory and energy footprint, making it suitable for low-resource deployment. Evaluated on the Factify-2 (5-class) and Mocheg (3-class) benchmarks, MultiCheck achieves huge performance improvement and remains robust under noisy OCR and missing modality conditions. Its efficiency, transparency, and real-world robustness make it well-suited for journalists, civil society organisations, and web integrity efforts working to build a safer and more trustworthy web.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05097
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MultiCheck: Strengthening Web Trust with Unified Multimodal Fact Verification
Kishore, Aditya
Kumar, Gaurav
Patro, Jasabanta
Computation and Language
Misinformation on the web increasingly appears in multimodal forms, combining text, images, and OCR-rendered content in ways that amplify harm to public trust and vulnerable communities. While prior fact-checking systems often rely on unimodal signals or shallow fusion strategies, modern misinformation campaigns operate across modalities and require models that can reason over subtle cross-modal inconsistencies in a transparent and responsible manner. We introduce MultiCheck, a lightweight and interpretable framework for multimodal fact verification that jointly analyzes textual, visual, and OCR evidence. At its core, MultiCheck employs a relational fusion module based on element-wise difference and product operations, allowing for explicit cross-modal interaction modeling with minimal computational overhead. A contrastive alignment objective further helps the model distinguish between supporting and refuting evidence while maintaining a small memory and energy footprint, making it suitable for low-resource deployment. Evaluated on the Factify-2 (5-class) and Mocheg (3-class) benchmarks, MultiCheck achieves huge performance improvement and remains robust under noisy OCR and missing modality conditions. Its efficiency, transparency, and real-world robustness make it well-suited for journalists, civil society organisations, and web integrity efforts working to build a safer and more trustworthy web.
title MultiCheck: Strengthening Web Trust with Unified Multimodal Fact Verification
topic Computation and Language
url https://arxiv.org/abs/2508.05097