{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:42:50Z","timestamp":1758588170702,"version":"3.44.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032063090"},{"type":"electronic","value":"9783032063106"}],"license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06310-6_1","type":"book-chapter","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T08:23:49Z","timestamp":1757924629000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Retrieval-Augmented Generation System for\u00a0Intelligent Question Answering"],"prefix":"10.1007","author":[{"given":"Bo","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yishuang","family":"Ning","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyu","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,14]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Yu, H., Yu, C., Wang, Z., Zou, D., Qin, H.: Enhancing healthcare through large language models: a study on medical question answering. In: 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS), pp. 895\u2013900. IEEE (2024)","DOI":"10.1109\/ICPICS62053.2024.10797141"},{"issue":"10","key":"1_CR2","doi-asserted-by":"publisher","first-page":"596","DOI":"10.3390\/info15100596","volume":"15","author":"R Sajja","year":"2024","unstructured":"Sajja, R., Sermet, Y., Cikmaz, M., Cwiertny, D., Demir, I.: Artificial intelligence-enabled intelligent assistant for personalized and adaptive learning in higher education. Information 15(10), 596 (2024)","journal-title":"Information"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, S., Ding, H., et\u00a0al.: Large language models in finance: a survey. In: Proceedings of the Fourth ACM International Conference on AI in Finance, pp. 374\u2013382 (2023)","DOI":"10.1145\/3604237.3626869"},{"issue":"20","key":"1_CR4","doi-asserted-by":"publisher","first-page":"3409","DOI":"10.3390\/electronics11203409","volume":"11","author":"B Liu","year":"2022","unstructured":"Liu, B., He, L., Liu, Y., Yu, T., Xiang, Y., Zhu, L., Ruan, W.: Transformer-based multimodal infusion dialogue systems. Electronics 11(20), 3409 (2022)","journal-title":"Electronics"},{"key":"1_CR5","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR6","unstructured":"Amazon Web Services. What is rag? Retrieval-augmented generation ai explained. https:\/\/aws.amazon.com\/what-is\/retrieval-augmented-generation\/ (2024). Accessed 17 May 2025"},{"key":"1_CR7","unstructured":"NVIDIA Technical Blog. Lost in the middle: improving llms\u2019 long-context retrieval using rag with nvidia nemo. https:\/\/developer.nvidia.com\/blog\/improving-llm-long-context-retrieval-using-rag-with-nvidia-nemo\/ (2023). Accessed 17 May 2025"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Liu, N.F., et al.: Lost in the middle: how language models use long contexts. arXiv preprint arXiv:2307.03172 (2023)","DOI":"10.1162\/tacl_a_00638"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Trappolini, G., Santilli, A., Rodol\u00e0, E., Halevy, A., Silvestri, F.: Multimodal neural databases. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2619\u20132628 (2023)","DOI":"10.1145\/3539618.3591930"},{"issue":"11","key":"1_CR10","doi-asserted-by":"publisher","first-page":"2031","DOI":"10.1109\/JAS.2022.105962","volume":"9","author":"B Liu","year":"2022","unstructured":"Liu, B., Song, R., Xiang, Y., Du, J., Ruan, W., Hu, J.: Self-supervised entity alignment based on multi-modal contrastive learning. IEEE\/CAA J. Autom. Sinica 9(11), 2031\u20132033 (2022)","journal-title":"IEEE\/CAA J. Autom. Sinica"},{"issue":"4","key":"1_CR11","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson, S., Zaragoza, H., et al.: The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr. 3(4), 333\u2013389 (2009)","journal-title":"Found. Trends Inf. Retr."},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: BGE m3-embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"1_CR13","unstructured":"Zhang, X., et al.: GME: improving universal multimodal retrieval by multimodal LLMs. arXiv preprint arXiv:2412.16855 (2024)"},{"key":"1_CR14","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"1_CR15","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"1_CR16","unstructured":"Yang, A., et\u00a0al.: Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"1_CR17","unstructured":"Qwen Team. Qwen2.5: a party of foundation models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/ (2024)"},{"key":"1_CR18","unstructured":"Mialon, G., et\u00a0al.: Augmented language models: a survey. arXiv preprint arXiv:2302.07842 (2023)"},{"key":"1_CR19","unstructured":"Li, C., Liu, Z., Xiao, S., Shao, Y.: Making large language models a better foundation for dense retrieval. arXiv preprint arXiv:2312.15503 (2023)"}],"container-title":["Lecture Notes in Computer Science","Cognitive Computing - ICCC 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06310-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T22:04:20Z","timestamp":1758578660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06310-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"ISBN":["9783032063090","9783032063106"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06310-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,14]]},"assertion":[{"value":"14 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that they have no known competing financial interests\u00a0or personal relationships that could have appeared to influence\u00a0the work reported in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cognitive Computing","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":"Hong Kong","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.servicessociety.org\/iccc","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}