mlsanityData to 14 Oct 2026

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

arXiv 2504.14493 ↗First posted 20 Apr 2025cs.IR cs.AI cs.LGcited by 19

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

Abstract (arXiv)

Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use. Within financial sectors, modern enterprises increasingly rely on Retrieval-Augmented Generation (RAG) systems to address complex compliance requirements in financial document workflows. However, existing solutions struggle to account for the inherent heterogeneity of data (e.g., text, tables, diagrams) and evolving nature of regulatory standards used in financial filings, leading to compromised accuracy in critical information extraction. We propose the FinSage framework as a solution, utilizing a multi-aspect RAG framework tailored for regulatory compliance analysis in multi-modal financial documents. FinSage introduces three innovative components: (1) a multi-modal pre-processing pipeline that unifies diverse data formats and generates chunk-level metadata summaries, (2) a multi-path sparse-dense retrieval system augmented with query expansion (HyDE) and metadata-aware semantic search, and (3) a domain-specialized re-ranking module fine-tuned via Direct Preference Optimization (DPO) to prioritize compliance-critical content. Extensive experiments demonstrate that FinSage achieves an impressive recall of 92.51% on 75 expert-curated questions derived from surpasses the best baseline method on the FinanceBench question answering datasets by 24.06% in accuracy. Moreover, FinSage has been successfully deployed as financial question-answering agent in online meetings, where it has already served more than 1,200 people.

Key facts. Cited by 19 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 29 of its 57 references that are in the map. First posted on arXiv 20 Apr 2025.

Builds on

29 of 57 references.

References · 29

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2017Billion-scale similarity search with GPUscited by 2,497
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  6. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  7. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  8. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 220
  9. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  10. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  11. 2024Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classificationcited by 70
  12. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
17 more
  1. 2024RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Modelscited by 60
  2. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documentscited by 49
  3. 2024BioRAG: A RAG-LLM Framework for Biological Question Reasoningcited by 43
  4. 2024RAGEval: Scenario Specific RAG Evaluation Dataset Generation Frameworkcited by 39
  5. 2024Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applicationscited by 31
  6. 2023Assessing the Quality of Multiple-Choice Questions Using GPT-4 and Rule-Based Methodscited by 24
  7. 2024A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADEcited by 18
  8. 2024Multi-Head RAG: Solving Multi-Aspect Problems with LLMscited by 18
  9. 2023Injecting the BM25 Score as Text Improves BERT-Based Re-rankerscited by 17
  10. 2024Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAGcited by 16
  11. 2023MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Modelcited by 10
  12. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoningcited by 8
  13. 2024Drowning in Documents: Consequences of Scaling Reranker Inferencecited by 8
  14. 2024The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typingcited by 6
  15. 2024Multi-Document Financial Question Answering using LLMscited by 6
  16. 2021Ensemble of MRR and NDCG models for Visual Dialogcited by 5
  17. 2024Domain-specific Question Answering with Hybrid Searchcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 11.

19 papers.

Sort:

By area:

  1. 2026Agentic Trading: When LLM Agents Meet Financial Marketscited by 7
  2. 2025Improving Context Fidelity via Native Retrieval-Augmented Reasoningcited by 5
  3. 2025Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reductioncited by 4
  4. 2025Structured RAG for Answering Aggregative Questionscited by 3
  5. 2025BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channelcited by 3
  6. 2025From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Developmentcited by 2
  7. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Modelscited by 2
  8. 2026SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliationcited by 2
  9. 2026AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verificationcited by 2
  10. 2025What Factors Affect LLMs and RLLMs in Financial Question Answering?cited by 1
  11. 2025A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMscited by 1
  12. 2026RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systemscited by 1
7 more
  1. 2026Agentic Graph Retrieval-Augmented Generation for Auditable Commercial Registry Analysiscited by 1
  2. 2026Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answeringcited by 0
  3. 2026EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answeringcited by 0
  4. 2026FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answeringcited by 0
  5. 2026VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documentscited by 0
  6. 2026FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QAcited by 0
  7. 2026Robust Hierarchical Structures for Agentic Document Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
  2. 2025FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval
  3. 2026HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings
  4. 2025Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems
  5. 2025VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
  6. 2025Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents
  7. 2025AstuteRAG-FQA: Task-Aware Retrieval-Augmented Generation Framework for Proprietary Data Challenges in Financial Question Answering
  8. 2026MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration