FinVet：面向金融虚假信息检测的检索增强生成与外部事实核查智能体协作框架
FinVet: A Collaborative Framework of RAG and External Fact-Checking Agents for Financial Misinformation Detection
AI总结：
针对金融虚假信息检测现有方法透明度低、溯源能力弱的问题，提出多智能体协作框架FinVet，融合RAG与外部事实核查，在FinFact数据集上F1达0.85，性能显著优于基线方法。
摘要：
金融市场正面临虚假信息带来的日益严重的威胁，这类信息可在数分钟内造成数十亿美元的损失。现有多数方法决策过程缺乏透明度，对可信来源的溯源支撑十分有限。本文提出新型多智能体框架FinVet，通过置信度加权投票机制融合两条检索增强生成（RAG）流水线与外部事实核查模块。FinVet采用自适应三层处理机制，可根据检索置信度动态调整核查策略，覆盖从直接元数据提取、混合推理到全模型分析的不同层级。与现有方法不同，FinVet可输出有证据支撑的判定结论、来源溯源、置信度分数，并在证据不足时给出明确的不确定性标记。在FinFact数据集上的实验评估显示，FinVet的F1分数达到0.85，较最优单流水线（事实核查流水线）提升10.4%，较独立RAG方法提升37%。
英文摘要：
Financial markets face growing threats from misinformation that can trigger billions in losses in minutes. Most existing approaches lack transparency in their decision-making and provide limited attribution to credible sources. We introduce FinVet, a novel multi-agent framework that integrates two Retrieval-Augmented Generation (RAG) pipelines with external fact-checking through a confidence-weighted voting mechanism. FinVet employs adaptive three-tier processing that dynamically adjusts verification strategies based on retrieval confidence, from direct metadata extraction to hybrid reasoning to full model-based analysis. Unlike existing methods, FinVet provides evidence-backed verdicts, source attribution, confidence scores, and explicit uncertainty flags when evidence is insufficient. Experimental evaluation on the FinFact dataset shows that FinVet achieves an F1 score of 0.85, which is a 10.4% improvement over the best individual pipeline (fact-check pipeline) and 37% improvement over standalone RAG approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
