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

arXiv: https://arxiv.org/abs/2504.14493 · HTML: https://mlsanity.com/paper/2504.14493/

## 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.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 29 of 29)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification](https://mlsanity.com/paper/2406.08660/) (2024)
- [Self-Knowledge Guided Retrieval Augmentation for Large Language Models](https://mlsanity.com/paper/2310.05002/) (2023)
- [RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models](https://mlsanity.com/paper/2407.05131/) (2024)
- [Improving Retrieval for RAG based Question Answering Models on Financial Documents](https://mlsanity.com/paper/2404.07221/) (2024)
- [BioRAG: A RAG-LLM Framework for Biological Question Reasoning](https://mlsanity.com/paper/2408.01107/) (2024)
- [RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework](https://mlsanity.com/paper/2408.01262/) (2024)
- [Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications](https://mlsanity.com/paper/2410.21943/) (2024)
- [Assessing the Quality of Multiple-Choice Questions Using GPT-4 and Rule-Based Methods](https://mlsanity.com/paper/2307.08161/) (2023)
- [A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE](https://mlsanity.com/paper/2403.10407/) (2024)
- [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://mlsanity.com/paper/2406.05085/) (2024)
- [Injecting the BM25 Score as Text Improves BERT-Based Re-rankers](https://mlsanity.com/paper/2301.09728/) (2023)
- [Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG](https://mlsanity.com/paper/2409.07691/) (2024)
- [MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model](https://mlsanity.com/paper/2310.13265/) (2023)
- [A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning](https://mlsanity.com/paper/2408.05141/) (2024)
- [Drowning in Documents: Consequences of Scaling Reranker Inference](https://mlsanity.com/paper/2411.11767/) (2024)
- [The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing](https://mlsanity.com/paper/2404.08313/) (2024)
- [Multi-Document Financial Question Answering using LLMs](https://mlsanity.com/paper/2411.07264/) (2024)
- [Ensemble of MRR and NDCG models for Visual Dialog](https://mlsanity.com/paper/2104.07511/) (2021)
- [Domain-specific Question Answering with Hybrid Search](https://mlsanity.com/paper/2412.03736/) (2024)

## Built on by (most cited first, 19 of 19)

- [Agentic Trading: When LLM Agents Meet Financial Markets](https://mlsanity.com/paper/2605.19337/) (2026)
- [Improving Context Fidelity via Native Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2509.13683/) (2025)
- [Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction](https://mlsanity.com/paper/2509.16369/) (2025)
- [Structured RAG for Answering Aggregative Questions](https://mlsanity.com/paper/2511.08505/) (2025)
- [BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel](https://mlsanity.com/paper/2511.12043/) (2025)
- [From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development](https://mlsanity.com/paper/2509.23071/) (2025)
- [Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models](https://mlsanity.com/paper/2511.18177/) (2025)
- [SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation](https://mlsanity.com/paper/2604.22294/) (2026)
- [AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification](https://mlsanity.com/paper/2606.03031/) (2026)
- [What Factors Affect LLMs and RLLMs in Financial Question Answering?](https://mlsanity.com/paper/2507.08339/) (2025)
- [A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs](https://mlsanity.com/paper/2509.09727/) (2025)
- [RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2603.10765/) (2026)
- [Agentic Graph Retrieval-Augmented Generation for Auditable Commercial Registry Analysis](https://mlsanity.com/paper/2605.18770/) (2026)
- [Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering](https://mlsanity.com/paper/2602.17981/) (2026)
- [EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering](https://mlsanity.com/paper/2606.23724/) (2026)
- [FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering](https://mlsanity.com/paper/2607.18102/) (2026)
- [VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents](https://mlsanity.com/paper/2609.11390/) (2026)
- [FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA](https://mlsanity.com/paper/2609.19680/) (2026)
- [Robust Hierarchical Structures for Agentic Document Analysis](https://mlsanity.com/paper/2609.33322/) (2026)

## 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.