ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction
It addresses the challenge of fake news detection for social stability and public trust, offering a novel approach to improve generalization for emerging topics, though it is incremental in combining retrieval and LLM techniques.
The paper tackles the problem of detecting fake news in fast-evolving news streams by proposing ZoFia, a zero-shot framework that uses entity-guided retrieval and multi-LLM interaction, achieving superior performance over existing zero-shot and most few-shot methods on two public datasets.
The rapid spread of fake news threatens social stability and public trust, rendering its detection an imperative research priority. Although large language models (LLMs) excel at numerous natural language processing tasks with their remarkable contextual understanding and extensive prior knowledge, the time-bounded knowledge coverage and tendency for generating hallucination content reduce their reliability when handling fast-evolving news streams. Furthermore, models trained on existing static datasets also often lack the generalization needed for emerging news topics. To address these challenges, we propose ZoFia, a novel two-stage zero-shot fake news detection framework. First, we introduce Hierarchical Salience to quantify the importance of entities in the news content, and propose the SC-MMR algorithm to effectively select an informative and diverse set of keywords that serve as queries for retrieving up-to-date external evidence. Subsequently, a multi LLM interactive system, in which each agent assumes a distinct role, performs multi-view collaborative analysis and adversarial debate over the news text and its related information, and finally produces an interpretable and robust judgment. Comprehensive experiments on two public datasets demonstrate that ZoFia obviously outperforms existing zero-shot baselines and most of few-shot methods. Our codes will be open-sourced to facilitate related communities.