用多智能体协作验证图文陈述真假，性能领先。
VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration
- 分阶段调用视觉语言模型智能体协同分析。
- 通过问答对生成实现跨模态证据整合，准确率领先。
- 适合需要高可信图文验证的新闻与社交平台使用。
本文介绍 VILLAIN，一个基于提示的多智能体协作多模态事实核查系统，用于验证图像-文本陈述。在 AVerImaTeC 共享任务中，VILLAIN 在多个阶段部署视觉-语言模型智能体。从通过额外网络采集增强的知识库中检索文本与视觉证据，模态专用及跨模态智能体分别生成分析报告以识别关键信息并解决证据间的不一致。随后，基于报告生成问题-答案对。最终，判决预测智能体结合图像-文本陈述与生成的问答对输出验证结果。本系统在所有评估指标上均位列榜首。源代码公开于 https://github.com/ssu-humane/VILLAIN。
原文摘要 · Abstract (English)
This paper describes VILLAIN, a multimodal fact-checking system that verifies image-text claims through prompt-based multi-agent collaboration. For the AVerImaTeC shared task, VILLAIN employs vision-language model agents across multiple stages of fact-checking. Textual and visual evidence is retrieved from the knowledge store enriched through additional web collection. To identify key information and address inconsistencies among evidence items, modality-specific and cross-modal agents generate analysis reports. In the subsequent stage, question-answer pairs are produced based on these reports. Finally, the Verdict Prediction agent produces the verification outcome based on the image-text claim and the generated question-answer pairs. Our system ranked first on the leaderboard across all evaluation metrics. The source code is publicly available at https://github.com/ssu-humane/VILLAIN.
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。