多智能体辩论框架让多媒体真伪验证过程透明可争辩。
Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification
- 用多智能体协作分解问题，生成带来源和强度的正反论证。
- 通过局部论点图解决冲突，支持不确定时升级处理。
- 输出可编辑的分段报告，适合需要透明推理的场景。
多媒体真伪验证不仅需要准确结论，还需透明且可争辩的推理过程。本文提出一种可争辩的多智能体框架，融合多模态大语言模型、外部验证工具与基于竞技场的量化双极论点框架（A-QBAF），提交至ICMR 2026多媒体验证挑战赛。方法将每个案例分解为以主张为中心的片段，检索针对性证据，并将证据转化为带有出处和强度评分的支持与攻击论点。这些论点通过小型局部论点图进行选择性冲突化解及不确定性感知的升级处理。最终系统生成分段式验证报告，具备透明性、可编辑性和计算可行性，适用于真实世界多媒体验证。实现代码已开源：https://github.com/Analytics-Everywhere-Lab/MV2026_the_liems。
原文摘要 · Abstract (English)
Multimedia verification requires not only accurate conclusions but also transparent and contestable reasoning. We propose a contestable multi-agent framework that integrates multimodal large language models, external verification tools, and arena-based quantitative bipolar argumentation (A-QBAF) as a submission to the ICMR 2026 Grand Challenge on Multimedia Verification. Our method decomposes each case into claim-centered sections, retrieves targeted evidence, and converts evidence into structured support and attack arguments with provenance and strength scores. These arguments are resolved through small local argument graphs with selective clash resolution and uncertainty-aware escalation. The resulting system generates section-wise verification reports that are transparent, editable, and computationally practical for real-world multimedia verification. Our implementation is public at: https://github.com/Analytics-Everywhere-Lab/MV2026_the_liems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。