KITE: A Tri-Modal Transformer Integrating Text, Images, and Knowledge Graphs for Fake News Detection

arXiv cs.LG Papers

Summary

Introduces KITE, a tri-modal transformer framework that jointly models text, images, and knowledge graphs for fake news detection, outperforming unimodal and bimodal baselines on benchmark datasets.

arXiv:2606.07651v1 Announce Type: new Abstract: Traditional fake news detection methods are falling behind as multimodal misinformation grows more advanced, seamlessly blending deceptive text, manipulated visuals, and factually incorrect claims. Most prior work focuses on text-image fusion or applies external knowledge only as a post-processing step, limiting their ability to detect deeper semantic inconsistencies. In this paper, we introduce KITE (Knowledge-Integrated Text-Image Encoder), a tri-modal fake news detection framework that jointly models textual, visual, and factual knowledge representations. KITE leverages Roberta [23,14] and CLIP [24] for linguistic and visual encoding, while a Graph Attention Network (GAT) processes structured facts retrieved from Wikidata. KITE uses cross-modal attention [9] within a multimodal transformer to integrate text, visual, and knowledge features, helping it understand how each modality relates to one another. Modality-specific confidence scores are generated alongside the final prediction, offering interpretability by indicating which input type most influenced the decision. Evaluations on benchmark datasets demonstrate that KITE significantly outperforms unimodal and bimodal baselines, particularly in scenarios involving image-text mismatches or contradictions with external knowledge.
Original Article
View Cached Full Text

Cached at: 06/09/26, 08:52 AM

# KITE: A Tri-Modal Transformer Integrating Text, Images, and Knowledge Graphs for Fake News Detection
Source: [https://arxiv.org/abs/2606.07651](https://arxiv.org/abs/2606.07651)
[View PDF](https://arxiv.org/pdf/2606.07651)

> Abstract:Traditional fake news detection methods are falling behind as multimodal misinformation grows more advanced, seamlessly blending deceptive text, manipulated visuals, and factually incorrect claims\. Most prior work focuses on text\-image fusion or applies external knowledge only as a post\-processing step, limiting their ability to detect deeper semantic inconsistencies\. In this paper, we introduce KITE \(Knowledge\-Integrated Text\-Image Encoder\), a tri\-modal fake news detection framework that jointly models textual, visual, and factual knowledge representations\. KITE leverages Roberta \[23,14\] and CLIP \[24\] for linguistic and visual encoding, while a Graph Attention Network \(GAT\) processes structured facts retrieved from Wikidata\. KITE uses cross\-modal attention \[9\] within a multimodal transformer to integrate text, visual, and knowledge features, helping it understand how each modality relates to one another\. Modality\-specific confidence scores are generated alongside the final prediction, offering interpretability by indicating which input type most influenced the decision\. Evaluations on benchmark datasets demonstrate that KITE significantly outperforms unimodal and bimodal baselines, particularly in scenarios involving image\-text mismatches or contradictions with external knowledge\.

## Submission history

From: Shashi Bhushan Jha \[[view email](https://arxiv.org/show-email/0ef97bd3/2606.07651)\] **\[v1\]**Tue, 2 Jun 2026 18:03:17 UTC \(680 KB\)

Similar Articles

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

Hugging Face Daily Papers

Introduces MulTaBench, a benchmark of 40 datasets for multimodal tabular learning with text and image modalities, demonstrating that task-specific embedding tuning improves performance over frozen pretrained embeddings, particularly when modalities provide complementary predictive signals.

UniT: Unified Geometry Learning with Group Autoregressive Transformer

Hugging Face Daily Papers

UniT is a unified feed-forward model for geometry perception using a Group Autoregressive Transformer that integrates multiple paradigms (online/offline, multi-modal, long-horizon) while maintaining metric-scale accuracy via scale-adaptive loss and queue-style KV caching. It achieves state-of-the-art performance on ten benchmarks spanning seven tasks.

Knowledge Graph-Enhanced Zero-Shot Topic Classification: A Multi-Strategy Comparative Study

arXiv cs.CL

This paper proposes a zero-shot multi-label topic classification framework enhanced with per-article knowledge graphs, comparing four base variants and their graph-augmented counterparts across fifteen LLMs and eight datasets. The study finds that keyword-enhanced classification performs best, and graph augmentation improves small models but degrades performance in larger ones.