Beyond Detection: Exploring Evidence-based Multi-Agent Debate for Misinformation Intervention and Persuasion

• URL: http://arxiv.org/abs/2511.07267v1
• Date: Mon, 10 Nov 2025 16:15:53 GMT
• Title: Beyond Detection: Exploring Evidence-based Multi-Agent Debate for Misinformation Intervention and Persuasion
• Authors: Chen Han, Yijia Ma, Jin Tan, Wenzhen Zheng, Xijin Tang,
• Abstract summary: Multi-agent debate (MAD) frameworks have emerged as promising approaches for simulating misinformation detection by adversarial reasoning.<n>We introduce ED2D, an evidence-based MAD framework that extends previous approach by incorporating factual evidence retrieval.<n>We compare the persuasive effects of ED2D-generated debunking transcripts with those authored by human experts.
• Score: 3.470521529046786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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, it overlooks the importance of helping users understand the reasoning behind factual judgments and develop future resilience. 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.

Related papers

• COMMUNITYNOTES: A Dataset for Exploring the Helpfulness of Fact-Checking Explanations [89.37527535663433]
  We present a large-scale dataset of 104k posts with user-provided notes and helpfulness labels.<n>We propose a framework that automatically generates and improves reason definitions via automatic prompt optimization.<n>Our experiments show that the optimized definitions can improve both helpfulness and reason prediction.
  arXiv  Detail & Related papers  (2025-10-28T05:28:47Z)
• Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection [81.52796950244705]
  Self-diagnosis is unreliable on complex tasks unless aided by reliable external feedback.<n>We introduce a new collaborative MAD protocol, termed ColMAD, that reframes MAD as a non-zero sum game.<n>We show that ColMAD significantly outperforms previous competitive MAD by 19%.
  arXiv  Detail & Related papers  (2025-10-23T19:46:00Z)
• ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety [87.90209836101353]
  ConspirED is the first dataset of conspiratorial content annotated for general cognitive traits.<n>We develop computational models that identify conspiratorial traits and determine dominant traits in text excerpts.<n>We evaluate large language/reasoning model (LLM/LRM) robustness to conspiratorial inputs.
  arXiv  Detail & Related papers  (2025-08-28T06:39:25Z)
• Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? [13.569822165805851]
  Multi-Agent Debate(MAD) has emerged as a promising paradigm for improving the performance of large language models.<n>Despite recent advances, the key factors driving MAD's effectiveness remain unclear.<n>We disentangle MAD into two key components--Majority Voting and inter-agent Debate--and assess their respective contributions.
  arXiv  Detail & Related papers  (2025-08-24T22:14:32Z)
• Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models [1.0091379815096075]
  We introduce Debate-to-Detect (D2D), a novel Multi-Agent Debate (MAD) framework that reformulates misinformation detection as a structured adversarial debate.<n>Inspired by fact-checking, 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.<n>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.
  arXiv  Detail & Related papers  (2025-05-24T08:44:33Z)
• Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models [65.23999399834638]
  We introduce DeceptionDecoded, a benchmark of 12,000 image-caption pairs grounded in trustworthy reference articles.<n>The dataset captures both misleading and non-misleading cases, spanning manipulations across visual and textual modalities.<n>It supports three intent-centric tasks: misleading intent detection, misleading source attribution, and creator desire inference.
  arXiv  Detail & Related papers  (2025-05-21T13:14:32Z)
• MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection [36.12673167913763]
  We introduce MAD-Sherlock, a multi-agent debate system for out-of-context misinformation detection.<n> MAD-Sherlock frames detection as a multi-agent debate, reflecting the diverse and conflicting discourse found online.<n>Our framework is domain- and time-agnostic, requiring no finetuning, yet achieves state-of-the-art accuracy with in-depth explanations.
  arXiv  Detail & Related papers  (2024-10-26T10:34:22Z)
• MisinfoEval: Generative AI in the Era of "Alternative Facts" [50.069577397751175]
  We introduce a framework for generating and evaluating large language model (LLM) based misinformation interventions. We present (1) an experiment with a simulated social media environment to measure effectiveness of misinformation interventions, and (2) a second experiment with personalized explanations tailored to the demographics and beliefs of users. Our findings confirm that LLM-based interventions are highly effective at correcting user behavior.
  arXiv  Detail & Related papers  (2024-10-13T18:16:50Z)
• Misinformation Has High Perplexity [55.47422012881148]
  We propose to leverage the perplexity to debunk false claims in an unsupervised manner. First, we extract reliable evidence from scientific and news sources according to sentence similarity to the claims. Second, we prime a language model with the extracted evidence and finally evaluate the correctness of given claims based on the perplexity scores at debunking time.
  arXiv  Detail & Related papers  (2020-06-08T15:13:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.