Multi-agent debate (MAD) frameworks have emerged as promising approaches for misinformation detection by simulating adversarial reasoning. While prior work has focused on detection accuracy, the importance of helping users understand the reasoning behind factual judgments has been overlooked. The debate transcripts generated during MAD offer a rich but underutilized resource for transparent reasoning. In this study, we introduce ED2D, an evidence-based MAD framework that extends previous approach by incorporating factual evidence retrieval. More importantly, ED2D is designed not only as a detection framework but also as a persuasive multi-agent system aimed at correcting user beliefs and discouraging misinformation sharing. We compare the persuasive effects of ED2D-generated debunking transcripts with those authored by human experts. Results demonstrate that ED2D outperforms existing baselines across three misinformation detection benchmarks. When ED2D generates correct predictions, its debunking transcripts exhibit persuasive effects comparable to those of human experts; However, when ED2D misclassifies, its accompanying explanations may inadvertently reinforce users’ misconceptions, even when presented alongside accurate human explanations. Our findings highlight both the promise and the potential risks of deploying MAD systems for misinformation intervention. We further develop a public community website to help users explore ED2D, fostering transparency, critical thinking, and collaborative fact-checking.

Chinese policy documents are typically written in a concise yet contextually rich style, containing implicit hierarchical logic and strategic intent. These linguistic and structural features present challenges for traditional information extraction methods, which often struggle with cross-sentence dependencies and semantic complexity. To address these, we propose DocPolicyKG, a novel framework for constructing knowledge graphs from Chinese policy documents using lightweight large language models (LLMs), integrating domain ontology, fine-tuning, and prompt engineering. Focusing on the investment promotion policies in China, experimental results demonstrate that DocPolicyKG significantly outperforms the base model Deepseek-R1-7B and achieves performance competitive with GPT-4o on both named entity recognition (NER) and relation triplet extraction (RTE) tasks. Building on DocPolicyKG, we construct the first large-scale knowledge graph of Chinese investment promotion policies, and further integrate Graph Retrieval-Augmented Generation (Graph RAG) to support policy question answering through entity-relation reasoning and semantic retrieval. The graph data is publicly available at: github.com/hanshenmesen/DocPolicyKG.

The proliferation of misinformation in digital platforms reveals the limitations of traditional detection methods, which mostly rely on static classification and fail to capture the intricate process of real-world fact-checking.Despite advancements in Large Language Models (LLMs) that enhance automated reasoning, their application to misinformation detection remains hindered by issues of logical inconsistency and superficial verification.Inspired by the idea that "Truth Becomes Clearer Through Debate", we introduce Debate-to-Detect (D2D), a novel Multi-Agent Debate (MAD) framework that reformulates misinformation detection as a structured adversarial debate.Based on fact-checking workflows, D2D assigns domain-specific profiles to each agent and orchestrates a five-stage debate process, including Opening Statement, Rebuttal, Free Debate, Closing Statement, and Judgment.To transcend traditional binary classification, D2D introduces a multi-dimensional evaluation mechanism that assesses each claim across five distinct dimensions: Factuality, Source Reliability, Reasoning Quality, Clarity, and Ethics.Experiments with GPT-4o on two fakenews datasets demonstrate significant improvements over baseline methods, and the case study highlight D2D's capability to iteratively refine evidence while improving decision transparency, representing a substantial advancement towards robust and interpretable misinformation detection.Our code is available at Debate-to-Detect.