KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: La, Tuan-Vinh, Nguyen, Minh-Hieu, Dao, Minh-Son
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912654923137024
author La, Tuan-Vinh
Nguyen, Minh-Hieu
Dao, Minh-Son
author_facet La, Tuan-Vinh
Nguyen, Minh-Hieu
Dao, Minh-Son
contents Fake news detection remains a challenging problem due to the complex interplay between textual misinformation, manipulated images, and external knowledge reasoning. While existing approaches have achieved notable results in verifying veracity and cross-modal consistency, two key challenges persist: (1) Existing methods often consider only the global image context while neglecting local object-level details, and (2) they fail to incorporate external knowledge and entity relationships for deeper semantic understanding. To address these challenges, we propose a novel multi-modal fake news detection framework that integrates visual, textual, and knowledge-based representations. Our approach leverages bottom-up attention to capture fine-grained object details, CLIP for global image semantics, and RoBERTa for context-aware text encoding. We further enhance knowledge utilization by retrieving and adaptively selecting relevant entities from a knowledge graph. The fused multi-modal features are processed through a Transformer-based classifier to predict news veracity. Experimental results demonstrate that our model outperforms recent approaches, showcasing the effectiveness of neighbor selection mechanism and multi-modal fusion for fake news detection. Our proposal introduces a new paradigm: knowledge-grounded multimodal reasoning. By integrating explicit entity-level selection and NLI-guided filtering, we shift fake news detection from feature fusion to semantically grounded verification. For reproducibility and further research, the source code is publicly at \href{https://github.com/latuanvinh1998/KGAlign}{github.com/latuanvinh1998/KGAlign}.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14714
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection
La, Tuan-Vinh
Nguyen, Minh-Hieu
Dao, Minh-Son
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Fake news detection remains a challenging problem due to the complex interplay between textual misinformation, manipulated images, and external knowledge reasoning. While existing approaches have achieved notable results in verifying veracity and cross-modal consistency, two key challenges persist: (1) Existing methods often consider only the global image context while neglecting local object-level details, and (2) they fail to incorporate external knowledge and entity relationships for deeper semantic understanding. To address these challenges, we propose a novel multi-modal fake news detection framework that integrates visual, textual, and knowledge-based representations. Our approach leverages bottom-up attention to capture fine-grained object details, CLIP for global image semantics, and RoBERTa for context-aware text encoding. We further enhance knowledge utilization by retrieving and adaptively selecting relevant entities from a knowledge graph. The fused multi-modal features are processed through a Transformer-based classifier to predict news veracity. Experimental results demonstrate that our model outperforms recent approaches, showcasing the effectiveness of neighbor selection mechanism and multi-modal fusion for fake news detection. Our proposal introduces a new paradigm: knowledge-grounded multimodal reasoning. By integrating explicit entity-level selection and NLI-guided filtering, we shift fake news detection from feature fusion to semantically grounded verification. For reproducibility and further research, the source code is publicly at \href{https://github.com/latuanvinh1998/KGAlign}{github.com/latuanvinh1998/KGAlign}.
title KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.14714