CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
CLAIR-Fin:用于跨模态金融问答中声明级验证与自适应辩论的对抗性多智能体框架
机构 * Ahsanullah University of Science and Technology(阿萨努拉科技大学) ; Jashore University of Science and Technology(杰索尔科技大学) ; American International University - Bangladesh(孟加拉国美国国际大学)
专题命中 多模态RAG :RAG(abstract,abstract_cn);retrieval-augmented generation(abstract);分类 cs.CL、cs.AI
AI总结 本研究提出CLAIR-Fin九智能体框架,针对跨模态金融问答的声明级验证与自适应辩论,在BB-FinQA-X数据集上提升了模型忠实度,且弃权比例合理,优于相关基线方法。