{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T14:31:44Z","timestamp":1787927504842,"version":"build-2784847793"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819219254","type":"print"},{"value":"9789819219261","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-1926-1_28","type":"book-chapter","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:53:09Z","timestamp":1782748389000},"page":"348-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal RAG: Text-Informed Cross-Modal Enhancement for\u00a0Efficient Local Deployment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7664-2347","authenticated-orcid":false,"given":"Chia-Yi","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0711-8197","authenticated-orcid":false,"given":"Ming-Syan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"28_CR2","unstructured":"Borgeaud, S., et al.: Improving language models by retrieving from trillions of tokens. In: International conference on machine learning, pp. 2206\u20132240. PMLR (2022)"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Caffagni, D., et al.: Wiki-LLaVA: hierarchical retrieval-augmented generation for multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1818\u20131826 (2024)","DOI":"10.1109\/CVPRW63382.2024.00188"},{"issue":"1","key":"28_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2071389.2071390","volume":"44","author":"C Carpineto","year":"2012","unstructured":"Carpineto, C., Romano, G.: A survey of automatic query expansion in information retrieval. Acm Comput. Surv. (CSUR) 44(1), 1\u201350 (2012)","journal-title":"Acm Comput. Surv. (CSUR)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Hu, H., Chen, X., Verga, P., Cohen, W.W.: MuRAG: multimodal retrieval-augmented generator for open question answering over images and text. arXiv preprint arXiv:2210.02928 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: Uniter: universal image-text representation learning. In: European Conference on Computer Vision, pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"28_CR7","unstructured":"Faysse, M., et al.: ColPali: efficient document retrieval with vision language models (2024). arXiv:2407.01449 arXiv preprint"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Gao, L., Ma, X., Lin, J., Callan, J.: Precise zero-shot dense retrieval without relevance labels. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1762\u20131777 (2023)","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"28_CR9","first-page":"39","volume":"34","author":"J Gu","year":"2021","unstructured":"Gu, J., et al.: Unidoc: unified pretraining framework for document understanding. Adv. Neural. Inf. Process. Syst. 34, 39\u201350 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Hong, T., et al.: Bros: a pre-trained language model focusing on text and layout for better key information extraction from documents. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"28_CR11","doi-asserted-by":"publisher","unstructured":"Izacard, G., Grave, E.: Leveraging passage retrieval with generative models for open domain question answering. In: Merlo, P., Tiedemann, J., Tsarfaty, R. (eds.) Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 874\u2013880. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.74. https:\/\/aclanthology.org\/2021.eacl-main.74\/","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. EMNLP (1), 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"28_CR13","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"28_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping Language-Image Pre-Training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"28_CR15","unstructured":"Lu, P., et al.: IconQA: a new benchmark for abstract diagram understanding and visual language reasoning (2021). arXiv:2110.13214 arXiv preprint"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Nan, L., et al.: OMG-QA: building open-domain multi-modal generative question answering systems. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pp. 1001\u20131015 (2024)","DOI":"10.18653\/v1\/2024.emnlp-industry.75"},{"key":"28_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"5","key":"28_CR19","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513\u2013523 (1988)","journal-title":"Inf. Process. Manag."},{"key":"28_CR20","unstructured":"Shi, W., et al.: REPLUG: retrieval-augmented black-box language models (2023). arXiv:2301.12652 arXiv preprint"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation (2021). arXiv:2104.07567 arXiv preprint","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"28_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834","volume":"144","author":"R Tito","year":"2023","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multipage DocVQA. Pattern Recogn. 144, 109834 (2023)","journal-title":"Pattern Recogn."},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Wang, L., Yang, N., Wei, F.: Query2doc: query expansion with large language models (2023). arXiv:2303.07678 arXiv preprint","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM Sigkdd International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"28_CR26","unstructured":"Yasunaga, M., et al.: Retrieval-augmented multimodal language modeling. arXiv preprint arXiv:2211.12561 (2022)"}],"container-title":["Lecture Notes in Computer Science","Data Science: Foundations and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1926-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T14:08:15Z","timestamp":1787926095000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1926-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"ISBN":["9789819219254","9789819219261"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1926-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"30 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}