Work

ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction

Year: 2026

Type: conference-paper

Abstract: The rapid spread of fake news threatens social stability and public trust, highlighting the urgent need for its effective detection.Although large language models (LLMs) show potential in fake news detection, they are limited by knowledge cutoff and easily generate factual hallucinations when handling timesensitive news.Furthermore, the thinking of a single LLM easily falls into early stance locking and confirmation bias, making it hard to handle both content reasoning and fact checking simultaneously.To address these challenges, we propose ZoFia, a two-stage zeroshot fake news detection framework.In the first retrieval stage, we propose novel Hierarchical Salience and Salience-Calibrated Minimum Marginal Relevance (SC-MMR) algorithm to extract core entities accurately, which drive dual-source retrieval to overcome knowledge and evidence gaps.In the subsequent stage, a multi-agent system conducts multiperspective reasoning and verification in parallel and achieves an explainable and robust result via adversarial debate.Comprehensive experiments on two public datasets show that ZoFia outperforms existing zero-shot baselines and even most few-shot methods.Our code has been open-sourced to facilitate the research community at https://github.com/ SakiRinn/ZoFia.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.1083