Cross-Domain Fake News Detection on Unseen Domains via LLM-Based Domain-Aware User Modeling

TL;DR

The paper tackles cross domain fake news detection in unseen domains by proposing DAUD, a two module framework that leverages LLM based domain aware enhancement and domain shared feature learning with relation aware alignment. The LDAE component extracts high level semantics from news and user engagements and augments engagement data, while the DSRA component disentangles domain specific noise and aligns news and user representations across domains. Empirical results on Politics, Entertainment and COVID-19 datasets show DAUD consistently improves over state of the art in both general and unseen domain settings, with ablations confirming the necessity of both LDAE and DSRA. The work demonstrates the practical potential of combining LLM driven semantic enrichment with structured cross domain representation learning for robust fake news detection in rapidly evolving, unlabeled target domains.

Abstract

Cross-domain fake news detection (CD-FND) transfers knowledge from a source domain to a target domain and is crucial for real-world fake news mitigation. This task becomes particularly important yet more challenging when the target domain is previously unseen (e.g., the COVID-19 outbreak or the Russia-Ukraine war). However, existing CD-FND methods overlook such scenarios and consequently suffer from the following two key limitations: (1) insufficient modeling of high-level semantics in news and user engagements; and (2) scarcity of labeled data in unseen domains. Targeting these limitations, we find that large language models (LLMs) offer strong potential for CD-FND on unseen domains, yet their effective use remains non-trivial. Nevertheless, two key challenges arise: (1) how to capture high-level semantics from both news content and user engagements using LLMs; and (2) how to make LLM-generated features more reliable and transferable for CD-FND on unseen domains. To tackle these challenges, we propose DAUD, a novel LLM-Based Domain-Aware framework for fake news detection on Unseen Domains. DAUD employs LLMs to extract high-level semantics from news content. It models users' single- and cross-domain engagements to generate domain-aware behavioral representations. In addition, DAUD captures the relations between original data-driven features and LLM-derived features of news, users, and user engagements. This allows it to extract more reliable domain-shared representations that improve knowledge transfer to unseen domains. Extensive experiments on real-world datasets demonstrate that DAUD outperforms state-of-the-art baselines in both general and unseen-domain CD-FND settings.

Figures (7)

• Figure 1: Our LLM-based approach provides advantages over existing approaches in both general and unseen-domain CD-FND settings.
• Figure 2: The learning process of DAUD framework.
• Figure 3: The overall architecture of DAUD framework.
• Figure 4: The architecture of Domain-Aware User Agent.
• Figure 5: Ablation Study of DAUD in unseen-domain CD-FND setting.