Rethink Rumor Detection in the Era of LLM：A Review

ACL ARR 2025 February Submission6110 Authors

Abstract: The rise of large language models (LLMs) has fundamentally reshaped the technological paradigm of rumor detection, offering transformative opportunities to construct adaptive detection systems while simultaneously ushering in new threats, such as "logically flawless" rumors. This paper focuses on modeling rumor detection in the era of LLMs by unifying existing methods in the field of rumor detection and uncovering their underlying logical mechanisms. From the perspective of complex systems, we innovatively propose a "Cognition-Interaction-Behavior" (CIB) tri-level framework for rumor detection based on collective intelligence and explore the synergistic relationship between LLMs and collective intelligence in rumor governance. Furthermore, we analyze the core challenges in the LLM era and outline future development pathways for social simulation agents. We hope this work lays a theoretical foundation for next-generation rumor detection paradigms and offers valuable insights for advancing the field.

Paper Type: Long

Research Area: Computational Social Science and Cultural Analytics

Research Area Keywords: misinformation detection and analysis

Languages Studied: english

Submission Number: 6110