Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering

TL;DR

This paper develops a metadata-driven Retrieval-Augmented Generation system tailored for financial document question answering, demonstrating that contextual embeddings and a multi-stage architecture significantly improve retrieval accuracy and efficiency.

Contribution

It introduces a novel multi-stage RAG architecture utilizing LLM-generated metadata and contextual embeddings, advancing retrieval precision in financial QA tasks.

Findings

Embedding metadata with text improves retrieval performance.

A powerful reranker enhances precision significantly.

The proposed system offers a cost-effective alternative to commercial solutions.

Abstract

Retrieval-Augmented Generation (RAG) struggles on long, structured financial filings where relevant evidence is sparse and cross-referenced. This paper presents a systematic investigation of advanced metadata-driven Retrieval-Augmented Generation (RAG) techniques, proposing and evaluating a novel, multi-stage RAG architecture that leverages LLM-generated metadata. We introduce a sophisticated indexing pipeline to create contextually rich document chunks and benchmark a spectrum of enhancements, including pre-retrieval filtering, post-retrieval reranking, and enriched embeddings, benchmarked on the FinanceBench dataset. Our results reveal that while a powerful reranker is essential for precision, the most significant performance gains come from embedding chunk metadata directly with text ("contextual chunks"). Our proposed optimal architecture combines LLM-driven pre-retrieval optimizations with these contextual embeddings to achieve superior performance. Additionally, we present a custom metadata reranker that offers a compelling, cost-effective alternative to commercial solutions, highlighting a practical trade-off between peak performance and operational efficiency. This study provides a blueprint for building robust, metadata-aware RAG systems for financial document analysis.