Breaking Event Rumor Detection via Stance-Separated Multi-Agent Debate
Preprint
Abstract
The rapid spread of rumors on social media platforms during breaking events severely hinders the dissemination of the truth. Previous studies reveal that the lack of annotated resources hinders the direct detection of unforeseen breaking events not covered in yesterday's news. Leveraging large language models (LLMs) for rumor detection holds significant promise. However, it is challenging for LLMs to provide comprehensive responses to complex or controversial issues due to limited diversity. In this work, we propose the Stance Separated Multi-Agent Debate (S2MAD) to address this issue. Specifically, we firstly introduce Stance Separation, categorizing comments as either supporting or opposing the original claim. Subsequently, claims are classified as subjective or objective, enabling agents to generate reasonable initial viewpoints with different prompt strategies for each type of claim. Debaters then follow specific instructions through multiple rounds of debate to reach a consensus. If a consensus is not reached, a judge agent evaluates the opinions and delivers a final verdict on the claim's veracity. Extensive experiments conducted on two real-world datasets demonstrate that our proposed model outperforms state-of-the-art methods in terms of performance and effectively improves the performance of LLMs in breaking event rumor detection.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models2024
- Enhancing large language model capabilities for rumor detection with Knowledge-Powered PromptingEngineering Applications of Artificial Intelligence, 2024
- Towards low-resource rumor detection: Unified contrastive transfer with propagation structureNeurocomputing, 2024
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate2024
- Adversarial Contrastive Learning for Evidence-Aware Fake News Detection With Graph Neural NetworksIEEE Transactions on Knowledge and Data Engineering, 2023
- Toward rumor detection in social networks using multi-layer autoencoder neural networkSocial Network Analysis and Mining, 2023
- KAGN:knowledge-powered attention and graph convolutional networks for social media rumor detectionJournal of Big Data, 2023
- Analysis of Techniques for Rumor Detection in Social MediaProcedia Computer Science, 2020
- A Psychology of RumorPublic Opinion Quarterly, 1944