Synergizing LLMs with Global Label Propagation for Multimodal Fake News Detection

2025-05-31

AI Summary

Large language models (LLMs) yield low-quality pseudo-labels for multimodal fake news detection, rendering them unsuitable for direct supervised training. Method: This paper proposes a synergistic framework integrating LLMs with global label propagation. It jointly leverages LLM-generated pseudo-labels, multimodal feature alignment, graph neural network (GNN)-based structural modeling, and global consistency propagation. Contribution/Results: The approach introduces two key innovations: (1) the first coupling mechanism between LLM-derived pseudo-labels and graph-structured global label propagation; and (2) a masked self-loop suppression strategy that prevents label leakage among training samples, thereby enhancing propagation robustness. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over state-of-the-art methods, validating the complementary benefits of semantic generation capability and structured reasoning in multimodal fake news detection.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Large Language Models (LLMs) can assist multimodal fake news detection by predicting pseudo labels. However, LLM-generated pseudo labels alone demonstrate poor performance compared to traditional detection methods, making their effective integration non-trivial. In this paper, we propose Global Label Propagation Network with LLM-based Pseudo Labeling (GLPN-LLM) for multimodal fake news detection, which integrates LLM capabilities via label propagation techniques. The global label propagation can utilize LLM-generated pseudo labels, enhancing prediction accuracy by propagating label information among all samples. For label propagation, a mask-based mechanism is designed to prevent label leakage during training by ensuring that training nodes do not propagate their own labels back to themselves. Experimental results on benchmark datasets show that by synergizing LLMs with label propagation, our model achieves superior performance over state-of-the-art baselines.

Problem

• Enhancing fake news detection using LLMs and label propagation
• Improving accuracy of LLM-generated pseudo labels via global propagation
• Preventing label leakage in training with mask-based mechanism

Innovation

• Integrates LLMs with label propagation
• Uses mask-based mechanism for label leakage prevention
• Enhances accuracy via global label propagation