{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:18:02Z","timestamp":1783102682787,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819699209","type":"print"},{"value":"9789819699216","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9921-6_31","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T06:16:07Z","timestamp":1753424167000},"page":"382-393","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Relevance: Utility-Driven Retrieval for Visual Document Question Answering"],"prefix":"10.1007","author":[{"given":"Bihui","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaowei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoya","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liping","family":"Bu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linzhuang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxuan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"31_CR1","unstructured":"Ding, Y., Lee, J., Han, S.: Deep learning based visually rich document content understanding: a survey. arXiv Preprint arXiv:2408.01287 (2024)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Yoshida, S.: VisualMRC: machine reading comprehension on document images. In: AAAI, pp. 13878\u201313888 (2021)","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Zhu, F., Lei, W., Feng, F., Wang, C., Zhang, H., Chua, T.S.: Towards complex document understanding by discrete reasoning. In: ACM MM, pp. 4857\u20134866 (2022)","DOI":"10.1145\/3503161.3548422"},{"key":"31_CR4","unstructured":"Cui, L., Xu, Y., Lv, T., Wei, F.: Document AI: benchmarks, models and applications. arXiv Preprint arXiv:2111.08609 (2021)"},{"key":"31_CR5","unstructured":"Jiang, T., et al.: E5-V: universal embeddings with multimodal large language models. arXiv Preprint arXiv:2407.12580 (2024)"},{"key":"31_CR6","unstructured":"Jiang, Z., Meng, R., Yang, X., Yavuz, S., Zhou, Y., Chen, W.: VLM2Vec: training vision-language models for massive multimodal embedding tasks. arXiv Preprint arXiv:2410.05160 (2024)"},{"key":"31_CR7","unstructured":"Yu, S., et al.: VisRAG: vision-based retrieval-augmented generation on multi-modality documents. arXiv Preprint arXiv:2410.10594 (2024)"},{"key":"31_CR8","unstructured":"Faysse, M., et al.: ColPali: efficient document retrieval with vision language models. arXiv Preprint arXiv:2407.01449 (2024)"},{"key":"31_CR9","unstructured":"Lee, J., Ko, J., Baek, J., Jeong, S., Hwang, S.J.: Unified multimodal interleaved document representation for retrieval. arXiv Preprint arXiv:2410.02729 (2024)"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Lin, W., Mei, J., Chen, J., Byrne, B.: PreFLMR: scaling up fine-grained late-interaction multi-modal retrievers. In: ACL, pp. 5294\u20135316 (2024)","DOI":"10.18653\/v1\/2024.acl-long.289"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: mPLUG-DocOwl2: high-resolution compressing for ocr-free multi-page document understanding. arXiv Preprint arXiv:2409.03420 (2024)","DOI":"10.18653\/v1\/2025.acl-long.291"},{"key":"31_CR12","unstructured":"Kandpal, N., Deng, H., Roberts, A., Wallace, E., Raffel, C.: Large language models struggle to learn long-tail knowledge. In: ICML, pp. 15696\u201315707 (2023)"},{"key":"31_CR13","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv Preprint arXiv:2312.10997 (2023)"},{"key":"31_CR14","unstructured":"Yao, Y., et al.: MiniCPM-V: a GPT-4V level MLLM on your phone. arXiv Preprint arXiv:2408.01800 (2024)"},{"key":"31_CR15","unstructured":"Tan, C., et al.: Retrieval meets reasoning: even high-school textbook knowledge benefits multimodal reasoning. arXiv Preprint arXiv:2405.20834 (2024)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: WACV, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"31_CR17","unstructured":"Liu, J., et al.: VisualWebBench: how far have multimodal LLMS evolved in web page understanding and grounding? arXiv Preprint arXiv:2404.05955 (2024)"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Katti, A.R., et al.: Chargrid: towards understanding 2D documents. In: EMNLP, pp. 4459\u20134469 (2018)","DOI":"10.18653\/v1\/D18-1476"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: TRIE: end-to-end text reading and information extraction for document understanding. In: ACM MM, pp. 1413\u20131422 (2020)","DOI":"10.1145\/3394171.3413900"},{"key":"31_CR20","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv Preprint arXiv:2303.08774 (2023)"},{"key":"31_CR21","unstructured":"Wang, P., et al.: Qwen2-Vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv Preprint arXiv:2409.12191 (2024)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Lauren\u00e7on, H., Marafioti, A., Sanh, V., Tronchon, L.: Building and better understanding vision-language models: insights and future directions. In: Workshop on Responsibly Building the Next Generation of Multimodal Foundational Models (2024)","DOI":"10.52202\/079017-2789"},{"key":"31_CR23","unstructured":"Chen, Z., et al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv Preprint arXiv:2412.05271 (2024)"},{"key":"31_CR24","unstructured":"Abdin, M., et al.: Phi-3 technical report: a highly capable language model locally on your phone. arXiv Preprint arXiv:2404.14219 (2024)"},{"key":"31_CR25","unstructured":"Li, B., et al.: Llava-onevision: easy visual task transfer. arXiv Preprint arXiv:2408.03326 (2024)"},{"key":"31_CR26","unstructured":"Team, G., et al.: Gemini1.5: unlocking multimodal understanding across millions of tokens of context. arXiv Preprint arXiv:2403.05530 (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9921-6_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:40:50Z","timestamp":1783100450000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9921-6_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819699209","9789819699216"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9921-6_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}