{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:26:56Z","timestamp":1763922416215,"version":"3.45.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093677","type":"print"},{"value":"9783032093684","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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\/978-3-032-09368-4_6","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:02Z","timestamp":1763921642000},"page":"92-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Document VQA Models via\u00a0Retrieval-Augmented Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3229-5739","authenticated-orcid":false,"given":"Eric","family":"L\u00f3pez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6128-1796","authenticated-orcid":false,"given":"Artemis","family":"Llabr\u00e9s","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0368-9697","authenticated-orcid":false,"given":"Ernest","family":"Valveny","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"6_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 (ICCV), pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Appalaraju, S., Tang, P., Dong, Q., Sankaran, N., Zhou, Y., Manmatha, R.: DocformerV2: local features for document understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 2, pp. 709\u2013718 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i2.27828, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/27828","DOI":"10.1609\/aaai.v38i2.27828"},{"key":"6_CR3","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. CoRR abs\/2502.13923 (2025). arXiv:2502.13923"},{"key":"6_CR4","unstructured":"Beyer, L., et al.: PaliGemma: a versatile 3B VLM for transfer. CoRR abs\/2407.07726 (2024). arXiv:2407.07726"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Blau, T., et al.: GRAM: Global reasoning for multi-page VQA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15598\u201315607 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01477","DOI":"10.1109\/CVPR52733.2024.01477"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: BGE M3-embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"6_CR7","unstructured":"Delestre, C.: (2024). https:\/\/huggingface.co\/cmarkea\/dit-base-layout-detection"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT (Vol. 1: Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"6_CR9","unstructured":"Faysse, M., et al.: COLPALI: efficient document retrieval with vision language models. In: Proceedings of the International Conference on Learning Representations (ICLR) (2025)"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR11","unstructured":"Henderson, M., et al.: Efficient natural language response suggestion for smart reply. CoRR abs\/1705.00652 (2017). arXiv:1705.00652"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMV3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia (ACM-MM) (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Kang, L., Tito, R., Valveny, E., Karatzas, D.: Multi-page document visual question answering using self-attention scoring mechanism. In: Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR) (2024)","DOI":"10.1007\/978-3-031-70552-6_13"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of the 43rd Int. ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 39\u201348 (2020). https:\/\/doi.org\/10.1145\/3397271.3401075","DOI":"10.1145\/3397271.3401075"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Landeghem, J.V., et al.: Document Understanding Dataset and Evaluation (DUDE). In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19528\u201319540 (2023)","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"6_CR16","unstructured":"Lee, K., et al.: Pix2struct: screenshot parsing as pretraining for visual language understanding. In: Proceedings of the 40th International Conference on Machine Learning (ICML) (2023)"},{"key":"6_CR17","unstructured":"Li, C., Liu, Z., Xiao, S., Shao, Y.: Making large language models a better foundation for dense retrieval (2023)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: MMLONGBENCH-doc: benchmarking long-context document understanding with visualizations. In: Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J., Zhang, C. (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 95963\u201396010. Curran Associates, Inc. (2024)","DOI":"10.52202\/079017-3041"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.V.: InfographicVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DOCVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2199\u20132208 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00225","DOI":"10.1109\/WACV48630.2021.00225"},{"issue":"140","key":"6_CR21","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR22","doi-asserted-by":"publisher","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Document collection visual question answering. In: Proceedings of the 16th International Conference on Document Analysis and Recognition (ICDAR). LNCS, vol. 12822, pp. 778\u2013792. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_50","DOI":"10.1007\/978-3-030-86331-9_50"},{"key":"6_CR23","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 multi-page DOCVQA. Pattern Recogn. 144, 109834 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2023.109834","journal-title":"Pattern Recogn."},{"key":"6_CR24","unstructured":"Verma, P.: S2 chunking: a hybrid framework for document segmentation through integrated spatial and semantic analysis. CoRR abs\/2501.05485 (2025). arXiv:2501.05485"},{"key":"6_CR25","unstructured":"Wang, D., et al.: DOCLLM: a layout-aware generative language model for multimodal document understanding. CoRR abs\/2401.00908 (2023). arXiv:2401.00908"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N.: C-pack: packaged resources to advance general Chinese embedding (2023)","DOI":"10.1145\/3626772.3657878"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMV2: multi-modal pre-training for visually-rich document understanding. In: Proceedings of ACL\/IJCNLP (Volume 1: Long Papers), pp. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"6_CR28","doi-asserted-by":"publisher","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: 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 (KDD), pp. 1192\u20131200 (2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"6_CR29","unstructured":"Zhao, Z., Kang, H., Wang, B., He, C.: DocLayout-YOLO: enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception. CoRR arXiv:2410.12628 (2024)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09368-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:05Z","timestamp":1763921645000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09368-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032093677","9783032093684"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09368-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","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":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}