{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T16:18:05Z","timestamp":1790093885591,"version":"4.0.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70533-5_17","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"280-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Embedding Layout in\u00a0Text for\u00a0Document Understanding Using Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7476-6533","authenticated-orcid":false,"given":"Mohammad","family":"Minouei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5974-3939","authenticated-orcid":false,"given":"Mohammad Reza","family":"Soheili","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"17_CR1","unstructured":"Deciai research team. 2024. DeciLM-7B-instruct. https:\/\/huggingface.co\/Deci\/DeciLM-7B-instruct"},{"key":"17_CR2","unstructured":"Tesseract open source OCR engine. https:\/\/github.com\/tesseract-ocr\/tesseract"},{"key":"17_CR3","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report (2023). arXiv preprint arXiv:2303.08774"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Breuel, T.M.: The hOCR microformat for OCR workflow and results. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007). vol.\u00a02, pp. 1063\u20131067. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4377078"},{"key":"17_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR6","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLORA: efficient finetuning of quantized LLMs. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). arXiv preprint arXiv:2010.11929"},{"key":"17_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1007\/978-3-030-86549-8_34","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"\u0141 Garncarek","year":"2021","unstructured":"Garncarek, \u0141, et al.: LAMBERT: layout-aware language modeling for information extraction. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 532\u2013547. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_34"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: XYLayoutLM: towards layout-aware multimodal networks for visually-rich document understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4583\u20134592 (2022)","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Gur, I., et al.: Understanding html with large language models (2022). arXiv preprint arXiv:2210.03945","DOI":"10.18653\/v1\/2023.findings-emnlp.185"},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Ha, J., Haralick, R., Phillips, I.: Recursive X-Y cut using bounding boxes of connected components. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol.\u00a02, pp. 952\u2013955 (1995). https:\/\/doi.org\/10.1109\/ICDAR.1995.602059","DOI":"10.1109\/ICDAR.1995.602059"},{"key":"17_CR12","unstructured":"Hu, E.J., et al.: LoRA: Low-rank adaptation of large language models (2021). arXiv preprint arXiv:2106.09685"},{"key":"17_CR13","unstructured":"Huang, L., et\u00a0al.: A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions (2023). arXiv preprint arXiv:2311.05232"},{"key":"17_CR14","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, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"17_CR15","doi-asserted-by":"publisher","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13688. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., et al.: FormNet: Structural encoding beyond sequential modeling in form document information extraction (2022). arXiv preprint arXiv:2203.08411","DOI":"10.18653\/v1\/2022.acl-long.260"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Li, Q., Li, Z., Cai, X., Du, B., Zhao, H.: Enhancing visually-rich document understanding via layout structure modeling. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4513\u20134523 (2023)","DOI":"10.1145\/3581783.3612327"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: StrucTexT: structured text understanding with multi-modal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1912\u20131920 (2021)","DOI":"10.1145\/3474085.3475345"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Luo, C., Cheng, C., Zheng, Q., Yao, C.: GeoLayoutLM: geometric pre-training for visual information extraction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7092\u20137101 (2023)","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"17_CR20","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S., Bossan, B.: PEFT: State-of-the-art parameter-efficient fine-tuning methods (2022). https:\/\/github.com\/huggingface\/peft"},{"key":"17_CR21","unstructured":"Naveed, H., et al.: A comprehensive overview of large language models (2023). arXiv preprint arXiv:2307.06435"},{"key":"17_CR22","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"17_CR23","unstructured":"Perot, V., et al.: LMDX: Language model-based document information extraction and localization (2023). arXiv preprint arXiv:2309.10952"},{"key":"17_CR24","unstructured":"Roziere, B., et\u00a0al.: Code Llama: Open foundation models for code (2023). arXiv preprint arXiv:2308.12950"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Sassioui, A., et al.: Visually-rich document understanding: concepts, taxonomy and challenges. In: 2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM), pp.\u00a01\u20137. IEEE (2023)","DOI":"10.1109\/WINCOM59760.2023.10322990"},{"key":"17_CR26","unstructured":"Touvron, H., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models (2023). arXiv preprint arXiv:2307.09288"},{"key":"17_CR27","unstructured":"Wang, Z., Zhou, Y., Wei, W., Lee, C.Y., Tata, S.: A benchmark for structured extractions from complex documents (2022). arXiv preprint arXiv:2211.15421"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding (2020). arXiv preprint arXiv:2012.14740","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"17_CR29","doi-asserted-by":"crossref","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, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70533-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:07:15Z","timestamp":1725685635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}