# MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering

arXiv: https://arxiv.org/abs/2506.20821 · HTML: https://mlsanity.com/paper/2506.20821/

## Key facts

- Cited by 9 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 18 of its 35 references that are in the map.
- First posted on arXiv 25 Jun 2025.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [Evaluating Retrieval Quality in Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.13781/) (2024)
- [Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models](https://mlsanity.com/paper/2409.04701/) (2024)
- [Financial Report Chunking for Effective Retrieval Augmented Generation](https://mlsanity.com/paper/2402.05131/) (2024)
- [Improving Automatic VQA Evaluation Using Large Language Models](https://mlsanity.com/paper/2310.02567/) (2023)
- [PDFTriage: Question Answering over Long, Structured Documents](https://mlsanity.com/paper/2309.08872/) (2023)
- [Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.18676/) (2024)
- [T-RAG: Lessons from the LLM Trenches](https://mlsanity.com/paper/2402.07483/) (2024)
- [Evaluating Quality of Answers for Retrieval-Augmented Generation: A Strong LLM Is All You Need](https://mlsanity.com/paper/2406.18064/) (2024)
- [FANAL -- Financial Activity News Alerting Language Modeling Framework](https://mlsanity.com/paper/2412.03527/) (2024)

## Built on by (most cited first, 9 of 9)

- [Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding](https://mlsanity.com/paper/2510.15253/) (2025)
- [Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems](https://mlsanity.com/paper/2511.16654/) (2025)
- [A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity](https://mlsanity.com/paper/2603.06976/) (2026)
- [Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrieval](https://mlsanity.com/paper/2605.31201/) (2026)
- [Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG](https://mlsanity.com/paper/2607.05438/) (2026)
- [AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and Reasoning](https://mlsanity.com/paper/2511.15578/) (2025)
- [SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats](https://mlsanity.com/paper/2512.04292/) (2025)
- [Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2603.00172/) (2026)
- [CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA](https://mlsanity.com/paper/2608.13706/) (2026)

## Abstract (arXiv)

Financial documents--such as 10-Ks, 10-Qs, and investor presentations--span hundreds of pages and combine diverse modalities, including dense narrative text, structured tables, and complex figures. Answering questions over such content often requires joint reasoning across modalities, which strains traditional large language models (LLMs) and retrieval-augmented generation (RAG) pipelines due to token limitations, layout loss, and fragmented cross-modal context. We introduce MultiFinRAG, a retrieval-augmented generation framework purpose-built for financial QA. MultiFinRAG first performs multimodal extraction by grouping table and figure images into batches and sending them to a lightweight, quantized open-source multimodal LLM, which produces both structured JSON outputs and concise textual summaries. These outputs, along with narrative text, are embedded and indexed with modality-aware similarity thresholds for precise retrieval. A tiered fallback strategy then dynamically escalates from text-only to text+table+image contexts when necessary, enabling cross-modal reasoning while reducing irrelevant context. Despite running on commodity hardware, MultiFinRAG achieves 19 percentage points higher accuracy than ChatGPT-4o (free-tier) on complex financial QA tasks involving text, tables, images, and combined multimodal reasoning.