A Dynamic Knowledge Update-Driven Model with Large Language Models for Fake News Detection

2025-09-15

AI Summary

Existing fake news detection methods struggle with the dynamic evolution of news veracity over time, knowledge obsolescence, and noise interference. Method: This paper proposes DYNAMO—a novel framework that (1) constructs a domain-specific knowledge graph for structured fact storage; (2) integrates large language models with retrieval-augmented generation (RAG) and employs Monte Carlo Tree Search for stepwise decomposition and semantic reasoning over complex news; and (3) enables continuous extraction, updating, and verification of new facts from verified authentic news. Contribution/Results: Experiments on two real-world datasets demonstrate that DYNAMO significantly outperforms state-of-the-art baselines in fake news detection, achieving new SOTA performance. It is the first approach to realize knowledge-graph-driven dynamic credibility modeling and incremental fact verification.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Misinformation & Fake News
• Data Mining & Knowledge Management: Knowledge Acquisition from the Web

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: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

As the Internet and social media evolve rapidly, distinguishing credible news from a vast amount of complex information poses a significant challenge. Due to the suddenness and instability of news events, the authenticity labels of news can potentially shift as events develop, making it crucial for fake news detection to obtain the latest event updates. Existing methods employ retrieval-augmented generation to fill knowledge gaps, but they suffer from issues such as insufficient credibility of retrieved content and interference from noisy information. We propose a dynamic knowledge update-driven model for fake news detection (DYNAMO), which leverages knowledge graphs to achieve continuous updating of new knowledge and integrates with large language models to fulfill dual functions: news authenticity detection and verification of new knowledge correctness, solving the two key problems of ensuring the authenticity of new knowledge and deeply mining news semantics. Specifically, we first construct a news-domain-specific knowledge graph. Then, we use Monte Carlo Tree Search to decompose complex news and verify them step by step. Finally, we extract and update new knowledge from verified real news texts and reasoning paths. Experimental results demonstrate that DYNAMO achieves the best performance on two real-world datasets.

Problem

• Detecting fake news amid rapidly evolving online information
• Addressing credibility issues in retrieved content for news verification
• Ensuring dynamic knowledge updates and semantic mining for accuracy

Innovation

• Leverages knowledge graphs for continuous knowledge updates
• Integrates large language models for dual detection functions
• Uses Monte Carlo Tree Search for stepwise news verification