Exploring Health Misinformation Detection with Multi-Agent Debate

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Chih-Han, Tsai, Chen-Han, Peng, Yu-Shao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917137847681024
author Chen, Chih-Han
Tsai, Chen-Han
Peng, Yu-Shao
author_facet Chen, Chih-Han
Tsai, Chen-Han
Peng, Yu-Shao
contents Fact-checking health-related claims has become increasingly critical as misinformation proliferates online. Effective verification requires both the retrieval of high-quality evidence and rigorous reasoning processes. In this paper, we propose a two-stage framework for health misinformation detection: Agreement Score Prediction followed by Multi-Agent Debate. In the first stage, we employ large language models (LLMs) to independently evaluate retrieved articles and compute an aggregated agreement score that reflects the overall evidence stance. When this score indicates insufficient consensus-falling below a predefined threshold-the system proceeds to a second stage. Multiple agents engage in structured debate to synthesize conflicting evidence and generate well-reasoned verdicts with explicit justifications. Experimental results demonstrate that our two-stage approach achieves superior performance compared to baseline methods, highlighting the value of combining automated scoring with collaborative reasoning for complex verification tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09935
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Health Misinformation Detection with Multi-Agent Debate
Chen, Chih-Han
Tsai, Chen-Han
Peng, Yu-Shao
Artificial Intelligence
Machine Learning
Fact-checking health-related claims has become increasingly critical as misinformation proliferates online. Effective verification requires both the retrieval of high-quality evidence and rigorous reasoning processes. In this paper, we propose a two-stage framework for health misinformation detection: Agreement Score Prediction followed by Multi-Agent Debate. In the first stage, we employ large language models (LLMs) to independently evaluate retrieved articles and compute an aggregated agreement score that reflects the overall evidence stance. When this score indicates insufficient consensus-falling below a predefined threshold-the system proceeds to a second stage. Multiple agents engage in structured debate to synthesize conflicting evidence and generate well-reasoned verdicts with explicit justifications. Experimental results demonstrate that our two-stage approach achieves superior performance compared to baseline methods, highlighting the value of combining automated scoring with collaborative reasoning for complex verification tasks.
title Exploring Health Misinformation Detection with Multi-Agent Debate
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2512.09935