面向可扩展金融RAG系统的分层重排序
Hierarchical Reranking for Scalable Financial RAG System
浏览论文内容
中文总结 AI 辅助
该研究针对现有RAG系统处理金融文档时的结构与规模难题，提出含三项创新的分层重排序器框架，在多金融基准测试中表现优异，获ACM-ICAIF '24金融RAG挑战赛第二名，可提升金融推理的准确性与可扩展性。
中文摘要 AI 辅助
分析10-K文件、表格披露和宏观经济报告等金融文档需要专业推理能力和大量时间。然而，现有的检索增强生成（Retrieval-Augmented Generation, RAG）系统往往难以处理混合文本-表格结构或金融文档的庞大规模。为应对这些挑战，我们提出了分层重排序器（Hierarchical Reranker），这是一种旨在提升大规模金融数据集上检索性能和生成可靠性的RAG框架。该系统整合了三项关键创新：预检索优化，通过规范化、关键词扩展和表格转换提升查询清晰度与搜索效率；分层重排序器架构，通过两阶段排序机制提升检索精度；以及长上下文管理，通过自适应输入分区与融合在海量上下文下保持推理准确性。在FinQA、FinanceBench和ConvFinQA等多个基准测试中，所提系统取得了0.7918的NDCG@20分数，并展现出更优的事实一致性。其鲁棒性进一步通过在ACM-ICAIF '24金融RAG挑战赛中获得第二名得到验证。本研究提出了一种可部署的、针对领域优化的RAG流水线，可提升金融推理的准确性与可扩展性，为自动化审计报告和量化投资分析铺平道路。源代码将在论文接收后在GitHub上公开。
英文摘要
Analyzing financial documents such as 10-K filings, tabular disclosures, and macroeconomic reports demands expert reasoning and extensive time. However, existing Retrieval-Augmented Generation systems often struggle to process hybrid text-table structures or the massive scale of financial documents. To address these challenges, we propose Hierarchical Reranker, a RAG framework designed to improve retrieval performance and generative reliability across large-scale financial datasets. The system integrates three key innovations: Pre-Retrieval Optimization, enhancing query clarity and search efficiency through normalization, keyword expansion, and table transformation; Hierarchical Reranker Architecture, improving retrieval precision through a two-stage ranking mechanism; and Long-Context Management, preserving reasoning accuracy through adaptive input partitioning and fusion under extensive contexts. Across multiple benchmarks, including FinQA, FinanceBench, and ConvFinQA, the proposed system achieved an NDCG@20 score of 0.7918 and demonstrated superior factual consistency. Its robustness was further validated by achieving second place in the ACM-ICAIF '24 FinanceRAG Challenge. This work presents a deployable, domain-optimized RAG pipeline that enhances both the accuracy and scalability of financial reasoning, paving the way for automated audit reporting and quantitative investment analysis. The source code will be made publicly available on GitHub upon acceptance.
发表机构
- Financial Security Institute（金融安全研究院）
- Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。
