Hierarchical Reranking for Scalable Financial RAG System

2026-07-29

AI Summary

This work addresses the challenges of low retrieval accuracy and insufficient generation reliability in existing retrieval-augmented generation (RAG) systems when handling large-scale, hybrid text-table documents in the financial domain. The authors propose a scalable, finance-oriented RAG framework that integrates pre-retrieval optimization, a two-stage hierarchical re-ranking mechanism, and an adaptive long-context partitioning and fusion strategy. Key innovations include query normalization, keyword expansion, and table structure transformation to enable efficient and precise domain-specific retrieval. Evaluated on FinQA, FinanceBench, and ConvFinQA, the system achieves an NDCG@20 of 0.7918, demonstrates significantly improved factual consistency over baseline methods, and secured second place in the ACM-ICAIF '24 FinanceRAG Challenge.

Abstract

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.

Problem

• Financial RAG
• Hybrid text-table structures
• Scalability
• Retrieval-Augmented Generation
• Financial document analysis

Innovation

• Hierarchical Reranking
• Retrieval-Augmented Generation
• Financial Document Understanding
• Long-Context Management
• Table-Text Hybrid Retrieval