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

TL;DR

MultiFinRAG is a specialized multimodal retrieval-augmented generation framework designed for financial question answering, effectively handling diverse content types and cross-modal reasoning on commodity hardware.

Contribution

It introduces a novel multimodal extraction and retrieval approach with a tiered fallback strategy, significantly improving accuracy over ChatGPT-4o on complex financial tasks.

Findings

Achieves 19 percentage points higher accuracy than ChatGPT-4o on financial QA.

Effectively handles text, tables, and images in a unified framework.

Operates efficiently on commodity hardware.

Abstract

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.