# MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering Source: [MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering]() Collection index: [llms.txt]() Data updated: 2026-04-14T05:00:04.234Z Authors: Chinmay Gondhalekar, Urjitkumar Patel, Fang-Chun Yeh Published: 2025-06-25T20:37:20.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Financial Question Answering on MultiFinRAG Text-based](): Financial Question Answering; MultiFinRAG Text-based; Accuracy: 90.4. - [Financial Question Answering on MultiFinRAG Image-based](): Financial Question Answering; MultiFinRAG Image-based; Accuracy: 66.7. - [Financial Question Answering on MultiFinRAG Table-based split](): Financial Question Answering; MultiFinRAG Table-based split; Accuracy: 69.4. - [Financial Question Answering on MultiFinRAG Text+Image Table-based](): Financial Question Answering; MultiFinRAG Text+Image Table-based; Accuracy: 40. - [Financial Question Answering on MultiFinRAG Total](): Financial Question Answering; MultiFinRAG Total; Accuracy: 75.3. ## Original sources and implementation [Original paper]() [PDF]()