The DOI matches its Crossref record.
Multimodal Retrieval-Augmented Generation: Unified Information Processing Across Text, Image, Table, and Video Modalities
Open accessAbstract
Retrieval-augmented generation (RAG) is a powerful paradigm for leveraging external data to enhance the capabilities of large language models (LLMs).However, most existing RAG solutions are tailored for single-modality or limited multimodal scenarios, restricting their applicability in real-world contexts where diverse data sources-including text, tables, images, and videos-must be integrated seamlessly.In this work, we propose a unified Multimodal Retrieval-augmented generation (mRAG) system designed to unify information processing across all four modalities.Our pipeline ingests and indexes data from PDFs and videos using tools like Amazon Textract, Transcribe, Langfuse, and multimodal LLMs (e.g., Claude 3.5 Sonnet) for structured extraction and semantic enrichment.The dataset includes text queries, table lookups, image-based questions, and videos.Evaluation with the Deepeval framework shows improved retrieval accuracy and response quality, especially for structured text and tables.While performance on image and video queries is lower, the multimodal integration framework remains robust, underscoring the value of unified pipelines for diverse data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Still being checked.
Cited by
Sorted by citations
Training Methods for Large Language Models: Current Approaches and Challenges
Karydas, D., Margaritis, D., & Leligou, H. C. (2026) · Technologies · doi:10.3390/technologies14020133 · Cited by 3
GenAI Multi-Agent Retrieval Augmented Generation for Oil & Gas Applications
Hnot, T., Nasr, H., & Zikrach, D. (2025) · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC) · doi:10.2118/229506-ms · Cited by 1
From Rows to Reasoning: A Retrieval-Augmented Multimodal Framework for Spreadsheet Understanding
Gulati, A., Sen, S., Sarguroh, W., & Paul, K. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817962 · Cited by 9
Shanivendra, A. C. (2026) · arXiv · doi:10.48550/arxiv.2603.14170
Ren, Y., Hu, M., Peng, N., Fang, X., Zhao, X. Y., & Wang, C. C. (2025) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec66174.2025.11331939
Metadata
- Authors
- Drushchak, N., Polyakovska, N., Bautina, M., Semenchenko, T., Koscielecki, J., Sykala, W., & Wegrzynowski, M.
- Affiliations
- SoftServe (United States) (US)
- Taras Shevchenko National University of Kyiv (UA)
- Venue
- Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)
- Published
- 2025
- Pages
- 59-64
- OpenAlex
- W4412944243
- Cited by
- 6
- References
- 0
- Citations by year
- 2026: 4 · 2025: 2
- FWCI
- 4.50
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- multimodal retrieval-augmented generation, multimodal retrieval, image-text retrieval, table retrieval, video retrieval, cross-modal retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
