COOL: Comprehensive Knowledge Enhanced Prompt Learning for Domain Adaptive Few-shot Fake News Detection

TL;DR

COOL introduces a novel prompt learning framework that leverages external knowledge and adversarial contrastive strategies to improve domain-adaptive few-shot fake news detection, addressing data scarcity and knowledge timeliness issues.

Contribution

The paper presents a comprehensive knowledge extraction module and an adversarial contrastive hybrid prompt learning strategy for enhanced fake news detection in limited data scenarios.

Findings

COOL outperforms state-of-the-art methods in domain-adaptive few-shot FND.

External knowledge integration improves detection accuracy.

Adversarial contrastive learning enhances domain-invariant feature modeling.

Abstract

Most Fake News Detection (FND) methods often struggle with data scarcity for emerging news domain. Recently, prompt learning based on Pre-trained Language Models (PLM) has emerged as a promising approach in domain adaptive few-shot learning, since it greatly reduces the need for labeled data by bridging the gap between pre-training and downstream task. Furthermore, external knowledge is also helpful in verifying emerging news, as emerging news often involves timely knowledge that may not be contained in the PLM's outdated prior knowledge. To this end, we propose COOL, a Comprehensive knOwledge enhanced prOmpt Learning method for domain adaptive few-shot FND. Specifically, we propose a comprehensive knowledge extraction module to extract both structured and unstructured knowledge that are positively or negatively correlated with news from external sources, and adopt an adversarial contrastive enhanced hybrid prompt learning strategy to model the domain-invariant news-knowledge interaction pattern for FND. Experimental results demonstrate the superiority of COOL over various state-of-the-arts.