mlsanityData to 14 Oct 2026

FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval

arXiv 2509.12042 ↗First posted 15 Sep 2025cs.CE cs.CLcited by 5

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

Abstract (arXiv)

Financial disclosures such as 10-K filings present challenging retrieval problems due to their length, regulatory section hierarchy, and domain-specific language, which standard retrieval-augmented generation (RAG) models underuse. We introduce FinGEAR (Financial Mapping-Guided Enhanced Answer Retrieval), a retrieval framework tailored to financial documents. FinGEAR combines a finance lexicon for Item-level guidance (FLAM), dual hierarchical indices for within-Item search (Summary Tree and Question Tree), and a two-stage cross-encoder reranker. This design aligns retrieval with disclosure structure and terminology, enabling fine-grained, query-aware context selection. Evaluated on full 10-Ks with queries aligned to the FinQA dataset, FinGEAR delivers consistent gains in precision, recall, F1, and relevancy, improving F1 by up to 56.7% over flat RAG, 12.5% over graph-based RAGs, and 217.6% over prior tree-based systems, while also increasing downstream answer accuracy with a fixed reader. By jointly modeling section hierarchy and domain lexicon signals, FinGEAR improves retrieval fidelity and provides a practical foundation for high-stakes financial analysis.

Key facts. Cited by 5 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 24 of its 32 references that are in the map. First posted on arXiv 15 Sep 2025.

Builds on

24 of 32 references.

References · 24

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2023BloombergGPT: A Large Language Model for Financecited by 939
  10. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  11. 2019ELI5: Long Form Question Answeringcited by 575
  12. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
12 more
  1. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  2. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  3. 2022Matryoshka Representation Learningcited by 282
  4. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 88
  5. 2024INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agentcited by 64
  6. 2024DocFinQA: A Long-Context Financial Reasoning Datasetcited by 60
  7. 2024In Defense of RAG in the Era of Long-Context Language Modelscited by 53
  8. 2024Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generationcited by 23
  9. 2024MANA-Net: Mitigating Aggregated Sentiment Homogenization with News Weighting for Enhanced Market Predictioncited by 6
  10. 2024Modeling News Interactions and Influence for Financial Market Predictioncited by 6
  11. 2017Replace or Retrieve Keywords In Documents at Scalecited by 3
  12. 2025FinBERT-QA: Financial Question Answering with pre-trained BERT Language Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Modelscited by 2
  2. 2025One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoningcited by 1
  3. 2026Aggregation Queries over Unstructured Text: Benchmark and Agentic Methodcited by 1
  4. 2026Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledgecited by 1
  5. 2026Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
  2. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
  3. 2026Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statements
  4. 2025Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems
  5. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
  6. 2024Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge
  7. 2025FinSage: A Multi-aspect RAG System for Financial Filings Question Answering
  8. 2024FinTextQA: A Dataset for Long-form Financial Question Answering