mlsanityData to 14 Oct 2026

Hierarchical Reranking for Scalable Financial RAG System

arXiv 2607.27523 ↗First posted 29 Jul 2026cs.IR cs.AIcited by 0

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

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 20 of its 25 references that are in the map. First posted on arXiv 29 Jul 2026.

Builds on

20 of 25 references.

References · 20

  1. 2024A Survey on LLM-as-a-Judgecited by 1,423
  2. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  3. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  4. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  5. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  6. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  7. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  8. 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answeringcited by 196
  9. 2023Compressing Context to Enhance Inference Efficiency of Large Language Modelscited by 189
  10. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  11. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 82
  12. 2023InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuningcited by 82
8 more
  1. 2024A Survey of Large Language Models in Finance (FinLLMs)cited by 79
  2. 2024Why Does the Effective Context Length of LLMs Fall Short?cited by 63
  3. 2023Query Expansion by Prompting Large Language Modelscited by 57
  4. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoningcited by 24
  5. 2025jina-reranker-v3: Last but Not Late Interaction for Listwise Document Rerankingcited by 24
  6. 2025Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMscited by 12
  7. 2024AI in Investment Analysis: LLMs for Equity Stock Ratingscited by 10
  8. 2025Ascendra: Dynamic Request Prioritization for Efficient LLM Servingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge
  2. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
  3. 2026Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis
  4. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
  5. 2026From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents
  6. 2025Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems
  7. 2024OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain
  8. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation