Agentic Multi-Persona Framework for Evidence-Aware Fake News Detection

TL;DR

This paper introduces AMPEND-LS, an innovative multimodal fake news detection framework that combines structured reasoning, evidence grounding, and credibility fusion to improve accuracy, robustness, and explainability in identifying misinformation.

Contribution

The paper presents AMPEND-LS, a novel agentic multi-persona framework integrating multimodal signals and reasoning techniques, advancing the state-of-the-art in fake news detection with enhanced reliability and transparency.

Findings

Outperforms existing methods in accuracy and robustness across benchmarks.

Effectively integrates textual, visual, and contextual evidence for improved detection.

Provides transparent reasoning and resilience against misinformation evolution.

Abstract

The rapid proliferation of online misinformation threatens the stability of digital social systems and poses significant risks to public trust, policy, and safety, necessitating reliable automated fake news detection. Existing methods often struggle with multimodal content, domain generalization, and explainability. We propose AMPEND-LS, an agentic multi-persona evidence-grounded framework with LLM-SLM synergy for multimodal fake news detection. AMPEND-LS integrates textual, visual, and contextual signals through a structured reasoning pipeline powered by LLMs, augmented with reverse image search, knowledge graph paths, and persuasion strategy analysis. To improve reliability, we introduce a credibility fusion mechanism combining semantic similarity, domain trustworthiness, and temporal context, and a complementary SLM classifier to mitigate LLM uncertainty and hallucinations. Extensive experiments across three benchmark datasets demonstrate that AMPEND-LS consistently outperformed state-of-the-art baselines in accuracy, F1 score, and robustness. Qualitative case studies further highlight its transparent reasoning and resilience against evolving misinformation. This work advances the development of adaptive, explainable, and evidence-aware systems for safeguarding online information integrity.