Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models

• URL: http://arxiv.org/abs/2505.18596v2
• Date: Tue, 27 May 2025 11:22:44 GMT
• Title: Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models
• Authors: Chen Han, Wenzhen Zheng, Xijin Tang,
• Abstract summary: 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> Experiments with GPT-4o on two fakenews datasets demonstrate significant improvements over baseline methods.
• Score: 0.8302146576157498
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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. In response, we introduce Debate-to-Detect (D2D), a novel Multi-Agent Debate (MAD) framework that reformulates misinformation detection as a structured adversarial debate. Inspired by 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. The code will be open-sourced in a future release.

Related papers

• Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents [13.626715532559079]
  We propose DebateCV, the first claim verification framework that adopts a debate-driven methodology using multiple LLM agents.<n>In our framework, two Debaters take opposing stances on a claim and engage in multi-round argumentation, while a Moderator evaluates the arguments and renders a verdict with justifications.<n> Experimental results show that our method outperforms existing claim verification methods under varying levels of evidence quality.
  arXiv  Detail & Related papers  (2025-07-25T09:19:25Z)
• Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection [11.917779863156097]
  Concept Drift (CD)-i.e., semantic or topical shifts alter the context or intent of interactions over time.<n>These shifts can obscure malicious intent or mimic normal dialogue, making accurate classification challenging.<n>We present a framework that integrates pretrained Large Language Models with structured, taskspecific insights to perform fraud and concept drift detection.
  arXiv  Detail & Related papers  (2025-06-26T16:29:45Z)
• Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval [1.515687944002438]
  The rapid spread of misinformation in the digital era poses significant challenges to public discourse.<n>Traditional human-led fact-checking methods, while credible, struggle with the volume and velocity of online content.<n>This paper proposes a novel multi-agent system for automated fact-checking that enhances accuracy, efficiency, and explainability.
  arXiv  Detail & Related papers  (2025-06-22T02:39:27Z)
• Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models [48.2311603411121]
  We introduce an automated framework that simulates real-world multimodal news creation by explicitly modeling creator intent.<n>DeceptionDecoded is a benchmark comprising 12,000 image-caption pairs aligned with trustworthy reference articles.<n>We conduct a comprehensive evaluation of 14 state-of-the-art vision-language models (VLMs) on three intent-centric tasks.
  arXiv  Detail & Related papers  (2025-05-21T13:14:32Z)
• Joint Detection of Fraud and Concept Drift inOnline Conversations with LLM-Assisted Judgment [11.917779863156097]
  We propose a two stage detection framework that first identifies suspicious conversations using a tailored ensemble classification model.<n>To improve the reliability of detection, we incorporate a concept drift analysis step using a One Class Drift Detector (OCDD)<n>When drift is detected, a large language model (LLM) assesses whether the shift indicates fraudulent manipulation or a legitimate topic change.
  arXiv  Detail & Related papers  (2025-05-07T22:30:53Z)
• DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models [31.15459303576494]
  We present Dynamic Self-Verify Decoding (DSVD), a novel decoding framework that enhances generation reliability through real-time hallucination detection and efficient error correction.<n>Our work establishes that real-time self-verification during generation offers a viable path toward more trustworthy language models without sacrificing practical deployability.
  arXiv  Detail & Related papers  (2025-03-05T03:45:50Z)
• Conditioned Prompt-Optimization for Continual Deepfake Detection [11.634681724245933]
  This paper introduces Prompt2Guard, a novel solution for photorealistic-free continual deepfake detection of images. We leverage a prediction ensembling technique with read-only prompts, mitigating the need for multiple forward passes. Our method exploits a text-prompt conditioning tailored to deepfake detection, which we demonstrate is beneficial in our setting.
  arXiv  Detail & Related papers  (2024-07-31T12:22:57Z)
• How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models [95.44559524735308]
  Large language or multimodal model based verification has been proposed to scale up online policing mechanisms for mitigating spread of false and harmful content. We test the limits of improving foundation model performance without continual updating through an initial study of knowledge transfer. Our results on two recent multi-modal fact-checking benchmarks, Mocheg and Fakeddit, indicate that knowledge transfer strategies can improve Fakeddit performance over the state-of-the-art by up to 1.7% and Mocheg performance by up to 2.9%.
  arXiv  Detail & Related papers  (2024-06-29T08:39:07Z)
• Detecting and Grounding Multi-Modal Media Manipulation and Beyond [93.08116982163804]
  We highlight a new research problem for multi-modal fake media, namely Detecting and Grounding Multi-Modal Media Manipulation (DGM4) DGM4 aims to not only detect the authenticity of multi-modal media, but also ground the manipulated content. We propose a novel HierArchical Multi-modal Manipulation rEasoning tRansformer (HAMMER) to fully capture the fine-grained interaction between different modalities.
  arXiv  Detail & Related papers  (2023-09-25T15:05:46Z)
• Give Me More Details: Improving Fact-Checking with Latent Retrieval [58.706972228039604]
  Evidence plays a crucial role in automated fact-checking. Existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. We propose to incorporate full text from source documents as evidence and introduce two enriched datasets.
  arXiv  Detail & Related papers  (2023-05-25T15:01:19Z)
• Verifying the Robustness of Automatic Credibility Assessment [50.55687778699995]
  We show that meaning-preserving changes in input text can mislead the models. We also introduce BODEGA: a benchmark for testing both victim models and attack methods on misinformation detection tasks. Our experimental results show that modern large language models are often more vulnerable to attacks than previous, smaller solutions.
  arXiv  Detail & Related papers  (2023-03-14T16:11:47Z)
• Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization [73.89239820192894]
  We argue that automated counterfactual generation should regard several aspects of the produced adversarial instances. We present a novel framework for the generation of counterfactual examples.
  arXiv  Detail & Related papers  (2022-05-20T15:02:53Z)
• Synthetic Disinformation Attacks on Automated Fact Verification Systems [53.011635547834025]
  We explore the sensitivity of automated fact-checkers to synthetic adversarial evidence in two simulated settings. We show that these systems suffer significant performance drops against these attacks. We discuss the growing threat of modern NLG systems as generators of disinformation.
  arXiv  Detail & Related papers  (2022-02-18T19:01:01Z)

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.