用智能体协同搜索，提升谣言检测准确率20%。
Web Retrieval Agents for Evidence-Based Misinformation Detection
- 双智能体协作：离线大模型+在线搜索，互补增强
- 相比纯大模型，谣言检测宏平均F1提升最高20%
- 分析了搜索来源偏见与证据类型对结果的影响
本文提出一种基于智能体的自动化谣言检测方法。我们证明，将无法联网的强大学习模型智能体与在线网络搜索智能体结合使用，效果优于单独使用任一工具。该方法在多个模型上表现稳健，显著优于其他方案，相比无搜索能力的大模型，谣言检测的宏平均F1最高提升20%。我们还深入分析了系统所依赖的信息源及其偏见、搜索工具与知识库的选择、所需证据类型及其影响等关键环节。通过高性能与深度理解的结合，为未来可检索的谣言防控系统提供基础构建模块。
原文摘要 · Abstract (English)
This paper develops an agent-based automated fact-checking approach for detecting misinformation. We demonstrate that combining a powerful LLM agent, which does not have access to the internet for searches, with an online web search agent yields better results than when each tool is used independently. Our approach is robust across multiple models, outperforming alternatives and increasing the macro F1 of misinformation detection by as much as 20 percent compared to LLMs without search. We also conduct extensive analyses on the sources our system leverages and their biases, decisions in the construction of the system like the search tool and the knowledge base, the type of evidence needed and its impact on the results, and other parts of the overall process. By combining strong performance with in-depth understanding, we hope to provide building blocks for future search-enabled misinformation mitigation systems.
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。