{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:11:40Z","timestamp":1774311100371,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032213204","type":"print"},{"value":"9783032213211","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-21321-1_10","type":"book-chapter","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T11:11:53Z","timestamp":1774264313000},"page":"74-81","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding Multi-Structured Documents via\u00a0LLMs\u2019"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7071-2344","authenticated-orcid":false,"given":"Shivani","family":"Upadhyay","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8145-812X","authenticated-orcid":false,"given":"Messiah","family":"Ataey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3330-4783","authenticated-orcid":false,"given":"Syed Shariyar","family":"Murtaza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9254-4735","authenticated-orcid":false,"given":"Yifan","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4735-9311","authenticated-orcid":false,"given":"Anirudh","family":"Aggarwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7189","authenticated-orcid":false,"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"10_CR1","unstructured":"Anthropic: The Claude 3 model family: Opus, Sonnet, Haiku"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: FinQA: a dataset of numerical reasoning over financial data. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.T. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3697\u20133711. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"10_CR3","unstructured":"Dai, X., et al.: EMU: enhancing image generation models using photogenic needles in a haystack. arXiv:2309.15807 (2023)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Dasigi, P., Lo, K., Beltagy, I., Cohan, A., Smith, N.A., Gardner, M.: A dataset of information-seeking questions and answers anchored in research papers. arXiv:2105.03011 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.365"},{"key":"10_CR5","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv:2312.10997 (2023)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Hoque, E., Kavehzadeh, P., Masry, A.: Chart question answering: state of the art and future directions. arXiv:2205.03966 (2022)","DOI":"10.1111\/cgf.14573"},{"key":"10_CR7","unstructured":"Hwang, W., Yim, J., Park, S., Seo, M.: A comprehensive exploration on WikiSQL with table-aware word contextualization. arXiv:1902.01069 (2019)"},{"key":"10_CR8","unstructured":"Jauhar, S.K., Turney, P., Hovy, E.: TabMCQ: a dataset of general knowledge tables and multiple-choice questions. arXiv:1602.03960 (2016)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Jin, N., Siebert, J., Li, D., Chen, Q.: A survey on table question answering: recent advances. arXiv:2207.05270 (2022)","DOI":"10.1007\/978-981-19-7596-7_14"},{"key":"10_CR10","unstructured":"Jin, Y., et al.: Unified language-vision pretraining with dynamic discrete visual tokenization. arXiv:2309.04669 (2023)"},{"key":"10_CR11","unstructured":"Kahou, S.E., Michalski, V., Atkinson, A., Kadar, A., Trischler, A., Bengio, Y.: FigureQA: an annotated figure dataset for visual reasoning. arXiv:1710.07300 (2018)"},{"key":"10_CR12","unstructured":"Lee, K., et al.: Pix2Struct: screenshot parsing as pretraining for visual language understanding. arXiv:2210.03347 (2023)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"10_CR14","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv:2304.08485 (2023)"},{"key":"10_CR15","unstructured":"L\u00e1la, J., O\u2019Donoghue, O., Shtedritski, A., Cox, S., Rodriques, S.G., White, A.D.: PaperQA: retrieval-augmented generative agent for scientific research. arXiv:2312.07559 (2023)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DocVQA: a dataset for VQA on document images. arXiv:2007.00398 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PlotQA: reasoning over scientific plots. arXiv:1909.00997 (2020)","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"10_CR19","unstructured":"Narayanan, S., et al.: Aviary: training language agents on challenging scientific tasks. arXiv:2412.21154 (2024)"},{"key":"10_CR20","unstructured":"Nguyen, P., Ly, N.T., Takeda, H., Takasu, A.: TabIQA: table questions answering on business document images. arXiv:2303.14935 (2023)"},{"key":"10_CR21","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv:2303.08774 (2024)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Pasupat, P., Liang, P.: Compositional semantic parsing on semi-structured tables. In: Zong, C., Strube, M. (eds.) Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1470\u20131480. Association for Computational Linguistics, Beijing, China (2015)","DOI":"10.3115\/v1\/P15-1142"},{"key":"10_CR23","unstructured":"Skarlinski, M.D., et al.: Language agents achieve superhuman synthesis of scientific knowledge. arXiv:2409.13740 (2024)"},{"key":"10_CR24","unstructured":"Sun, Q., et al.: Generative multimodal models are in-context learners. arXiv:2312.13286 (2023)"},{"key":"10_CR25","unstructured":"Anil, R., et al.: Gemini: a family of highly capable multimodal models. arXiv:2312.11805 (2024)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Document Collection Visual Question Answering, pp. 778\u2013792. Springer (2021)","DOI":"10.1007\/978-3-030-86331-9_50"},{"key":"10_CR27","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv:2302.13971 (2023)"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Xia, R., et al.: ChartX & ChartVLM: a versatile benchmark and foundation model for complicated chart reasoning. arXiv:2402.12185 (2024)","DOI":"10.1109\/TIP.2025.3607618"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, F., et al.: TAT-QA: a question answering benchmark on a hybrid of tabular and textual content in finance. arXiv:2105.07624 (2021)","DOI":"10.18653\/v1\/2021.acl-long.254"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21321-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:18:35Z","timestamp":1774307915000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21321-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032213204","9783032213211"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21321-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"24 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Some authors were employed by Manulife during this work. The authors declare no other competing interests relevant to this work. Funding is listed in the Acknowledgements.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}