{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:37:17Z","timestamp":1772933837402,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100031060","name":"EuroHPC JU","doi-asserted-by":"publisher","award":["101101903"],"award-info":[{"award-number":["101101903"]}],"id":[{"id":"10.13039\/100031060","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004329","name":"Slovenian Research Agency","doi-asserted-by":"publisher","award":["GC-0001"],"award-info":[{"award-number":["GC-0001"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401037","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"5156-5165","source":"Crossref","is-referenced-by-count":0,"title":["Exploration of Augmentation Strategies in Multi-Modal Retrieval-Augmented Generation for the Biomedical Domain*: *A Case Study Evaluating Question Answering in Glycobiology"],"prefix":"10.1109","author":[{"given":"Primo\u017e","family":"Kocbek","sequence":"first","affiliation":[{"name":"University of Maribor,Faculty of Health Sciences,Maribor,Slovenia"}]},{"given":"Azra","family":"Frkatovi\u0107-Hod\u017ei\u0107","sequence":"additional","affiliation":[{"name":"Genos Ltd,Zagreb,Croatia"}]},{"given":"Dora","family":"Lali\u0107","sequence":"additional","affiliation":[{"name":"Genos Ltd,Zagreb,Croatia"}]},{"given":"Vivian","family":"Hui","sequence":"additional","affiliation":[{"name":"School of Nursing, The Hong Kong Polytechnic University,Center for Smart Health,Hong Kong,China"}]},{"given":"Gordan","family":"Lauc","sequence":"additional","affiliation":[{"name":"Genos Ltd,Zagreb,Croatia"}]},{"given":"Gregor","family":"\u0160tiglic","sequence":"additional","affiliation":[{"name":"University of Maribor,Faculty of Health Sciences,Maribor,Slovenia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-015-0564-6"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"2567","DOI":"10.18653\/v1\/D19-1259","article-title":"Pubmedqa: A dataset for biomedical research question answering","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Jin","year":"2019"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.emnlp-main.15","article-title":"Fine-tuning or retrieval? comparing knowledge injection in 11 ms","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Ovadia","year":"2024"},{"key":"ref5","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 (NeurIPS 2020)"},{"issue":"7","key":"ref6","first-page":"687","article-title":"Retrieval-augmented generation in biomedical informatics","volume":"12","author":"Editors","year":"2024","journal-title":"Biomedicines"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00018-010-0352-4"},{"issue":"8","key":"ref8","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1093\/glycob\/cwad064","article-title":"Can chatgpt pass glycobiology?","volume":"33","author":"Williams","year":"2023","journal-title":"Glycobiology"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104662"},{"key":"ref10","article-title":"Colpali: Efficient document retrieval with vision language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Faysse","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref12","article-title":"Visrag: Vision-based retrieval-augmented generation on multi-modality documents","volume-title":"International Conference on Learning Representations (ICLR)","volume":"2025","author":"Yu","year":"2025"},{"key":"ref13","article-title":"Colflor: Towards bert-size vision-language document retrieval models","author":"Masry","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","volume-title":"Colqwen2-v0.2: Vision-language document retrieval","author":"Team","year":"2025"},{"key":"ref15","volume-title":"Multimodal medical ai","year":"2023"},{"issue":"1","key":"ref16","doi-asserted-by":"crossref","first-page":"qzaf011","DOI":"10.1093\/gpbjnl\/qzaf011","article-title":"A comprehensive review of ai in multimodal biomedical data analysis","volume":"23","author":"Li","year":"2024","journal-title":"Genomics, Proteomics & Bioinformatics"},{"key":"ref17","article-title":"Llava-med: Training a large language-andvision assistant for biomedicine in one day","volume-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023), Datasets and Benchmarks Track","author":"Li","year":"2023"},{"key":"ref18","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","volume-title":"Proceedings of the Machine Learning for Health (MLAH) 2023","volume":"225","author":"Moor","year":"2023"},{"key":"ref19","article-title":"Towards generalist biomedical ai","author":"Tu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/ai6090226"},{"key":"ref22","article-title":"Biomedical literature q&a system using retrieval-augmented generation (rag)","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref23","volume-title":"Biomedical literature q&a system using retrievalaugmented generation (rag)","year":"2025"},{"key":"ref24","article-title":"Medgpt: A modular chatbot for medical diagnostics","volume-title":"Proceedings of the 2024 International Conference on Intelligent Systems and Machine Learning (ISML)","author":"Sree","year":"2024"},{"key":"ref25","article-title":"Mrag-bench: Vision-centric evaluation for retrieval-augmented multimodal models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hu","year":"2025"},{"key":"ref26","article-title":"On domain-specific post-training for multimodal large language models","author":"Cheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","volume-title":"Llama 3.2: Revolutionizing edge ai and vision with open, customizable models","year":"2024"},{"key":"ref30","article-title":"Gemma 3 technical report","author":"Kamath","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref32","volume-title":"Enterprise privacy at openai","year":"2025"},{"key":"ref33","article-title":"Docling technical report","author":"Auer","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","volume-title":"Qdrant: Open-source vector database and vector search engine","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"ref36","article-title":"Vidore benchmark v2: Raising the bar for visual retrieval","author":"Mac\u00e9","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref37","volume-title":"vidore\/colpali-v1.3-merged","year":"2025"},{"key":"ref38","volume-title":"Colpali model documentation in hugging face transformers","year":"2025"},{"key":"ref39","volume-title":"manu\/colqwen2-v0.2","year":"2025"},{"key":"ref40","volume-title":"ahmed-masry\/colflor model card","year":"2024"},{"key":"ref41","volume-title":"Colflor: Towards bert-size vision-language document retrieval models","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/2685469"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401037.pdf?arnumber=11401037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:53:13Z","timestamp":1772866393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401037","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}