mlsanityData to 14 Oct 2026

Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering

arXiv 2510.24402 ↗First posted 28 Oct 2025cs.IR cs.AI cs.CEcited by 4

On the map: Retrieval-augmented generation → Legal and financial RAG

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 60 of its 86 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

60 of 86 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation22 Apr

Other references · 59

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  10. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  11. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  12. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
38 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  3. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  4. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  5. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  6. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  7. 2019Passage Re-ranking with BERTcited by 645
  8. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  9. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  10. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  11. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  12. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  13. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  14. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
  15. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  16. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  17. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  18. 2023FinGPT: Open-Source Financial Large Language Modelscited by 253
  19. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  20. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  21. 2019Document Expansion by Query Predictioncited by 231
  22. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  23. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  24. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  25. 2020FinBERT: A Pretrained Language Model for Financial Communicationscited by 161
  26. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  27. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 119
  28. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 108
  29. 2022Re2G: Retrieve, Rerank, Generatecited by 102
  30. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrieverscited by 84
  31. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  32. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generationcited by 75
  33. 2024RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generationcited by 61
  34. 2024DocFinQA: A Long-Context Financial Reasoning Datasetcited by 60
  35. 2023Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Modelscited by 58
  36. 2025Knowledge Graph-Guided Retrieval Augmented Generationcited by 58
  37. 2024FinTextQA: A Dataset for Long-form Financial Question Answeringcited by 54
  38. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivitycited by 3
  2. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Modelscited by 2
  3. 2026Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detectorcited by 2
  4. 2026A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrievalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems
  2. 2026Hierarchical Reranking for Scalable Financial RAG System
  3. 2024Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge
  4. 2026Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering
  5. 2026Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis
  6. 2025VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
  7. 2026HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings
  8. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documents