Detect, Investigate, Judge and Determine: A Knowledge-guided Framework for Few-shot Fake News Detection

2024-07-12

AI Summary

This work addresses few-shot fake news detection (FS-FND) under extremely low-resource settings (1–5 samples per class). To tackle this challenge, we propose DKFND, a dual-perspective knowledge-guided framework. Methodologically, DKFND introduces a novel four-stage, knowledge-driven paradigm—“detect–investigate–evaluate–decide”—that jointly models parametric knowledge internal to the model and external knowledge retrieved via retrieval augmentation, implemented through a modular architecture enabling interpretable, chain-of-reasoning inference. The approach integrates knowledge concept identification, multi-source knowledge retrieval, joint relevance and confidence assessment, and multi-path prediction fusion. Evaluated on two public benchmarks, DKFND consistently outperforms state-of-the-art few-shot methods, achieving up to a 12.6% absolute accuracy improvement. These results empirically validate the effectiveness and generalizability of knowledge-guided strategies for fake news identification in data-scarce regimes.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Knowledge Acquisition from the Web
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Few-Shot Fake News Detection (FS-FND) aims to distinguish inaccurate news from real ones in extremely low-resource scenarios. This task has garnered increased attention due to the widespread dissemination and harmful impact of fake news on social media. Large Language Models (LLMs) have demonstrated competitive performance with the help of their rich prior knowledge and excellent in-context learning abilities. However, existing methods face significant limitations, such as the Understanding Ambiguity and Information Scarcity, which significantly undermine the potential of LLMs. To address these shortcomings, we propose a Dual-perspective Knowledge-guided Fake News Detection (DKFND) model, designed to enhance LLMs from both inside and outside perspectives. Specifically, DKFND first identifies the knowledge concepts of each news article through a Detection Module. Subsequently, DKFND creatively designs an Investigation Module to retrieve inside and outside valuable information concerning to the current news, followed by another Judge Module to evaluate the relevance and confidence of them. Finally, a Determination Module further derives two respective predictions and obtain the final result. Extensive experiments on two public datasets show the efficacy of our proposed method, particularly in low-resource settings.

Problem

• Detect fake news in low-resource scenarios
• Overcome understanding ambiguity and information scarcity
• Enhance LLMs with dual-perspective knowledge guidance

Innovation

• Dual-perspective knowledge-guided model
• Detection, Investigation, Judge, Determination modules
• Enhances LLMs in low-resource scenarios