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

[2506.20821] MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2506.20821 (cs) [Submitted on 25 Jun 2025] Title: MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering Authors: Chinmay Gondhalekar , Urjitkumar Patel , Fang-Chun Yeh View a PDF of the paper titled MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering, by Chinmay Gondhalekar and 2 other authors View PDF HTML (experimental) 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. Comments: Preprint Copy Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE) MSC classes: 68T50, 68T07 (Primary) 68P20, 91G15, 91G70, 68U10 (Secondary) ACM classes: I.2.7; I.2.10; H.3.3; H.2.8; I.5.4; J.1 Cite as: arXiv:2506.20821 [cs.CL] (or arXiv:2506.20821v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2506.20821 Focus to learn more arXiv-issued DOI via DataCite Journal reference: 2025 IEEE International Conference on Big Data (BigData), Macau, China Related DOI : https://doi.org/10.1109/BigData66926.2025.11401444 Focus to learn more DOI(s) linking to related resources Submission history From: Urjitkumar Patel [ view email ] [v1] Wed, 25 Jun 2025 20:37:20 UTC (2,203 KB) Full-text links: Access Paper: View a PDF of the paper titled MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering, by Chinmay Gondhalekar and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2025-06 Change to browse by: cs cs.AI cs.CE References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models#130767
• NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance#1142547
• FinSentGPT: A universal financial sentiment engine?#226484
• Benchmarking Large Language Models in Retrieval-Augmented Generation#328727
• FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings#440412