Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915582881824768 |
|---|---|
| author | Dadopoulos, Michail Ladas, Anestis Moschidis, Stratos Negkakis, Ioannis |
| author_facet | Dadopoulos, Michail Ladas, Anestis Moschidis, Stratos Negkakis, Ioannis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24402 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering Dadopoulos, Michail Ladas, Anestis Moschidis, Stratos Negkakis, Ioannis Information Retrieval Artificial Intelligence Computational Engineering, Finance, and Science 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. |
| title | Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering |
| topic | Information Retrieval Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2510.24402 |