{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:04:25Z","timestamp":1779991465998,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","funder":[{"name":"ARC Training Centre in Critical Resources for the Future","award":["IC230100035"],"award-info":[{"award-number":["IC230100035"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3774905.3793117","type":"proceedings-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:14:56Z","timestamp":1779988496000},"page":"124-127","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Docs2Synth: A Synthetic Data Tuned Retriever Framework for Documents Understanding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5065-6911","authenticated-orcid":false,"given":"Yihao","family":"Ding","sequence":"first","affiliation":[{"name":"University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4445-0025","authenticated-orcid":false,"given":"Qiang","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1510-215X","authenticated-orcid":false,"given":"Puzhen","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2504-3790","authenticated-orcid":false,"given":"Sirui","family":"Li","sequence":"additional","affiliation":[{"name":"Murdoch University, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0480-1991","authenticated-orcid":false,"given":"Siwen","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7409-0948","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Western Australia, Perth, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.748"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.14238"},{"key":"e_1_3_2_1_3_1","volume-title":"Zechuan Li, and Hyunsuk Chung.","author":"Ding Yihao","year":"2025","unstructured":"Yihao Ding, Soyeon Caren Han, Zechuan Li, and Hyunsuk Chung. 2025a. SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction. Information Fusion (2025), 104074."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591886"},{"key":"e_1_3_2_1_5_1","volume-title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends. arXiv preprint arXiv:2507.09861","author":"Ding Yihao","year":"2025","unstructured":"Yihao Ding, Siwen Luo, Yue Dai, Yanbei Jiang, Zechuan Li, Geoffrey Martin, and Yifan Peng. 2025b. A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends. arXiv preprint arXiv:2507.09861 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.11810"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"e_1_3_2_1_8_1","unstructured":"Anwen Hu Haiyang Xu Liang Zhang Jiabo Ye Ming Yan Ji Zhang Qin Jin Fei Huang and Jingren Zhou. 2024b. mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding. arXiv:2409.03420 [cs.CV] https:\/\/arxiv.org\/abs\/2409.03420"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_10_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Lauren\u00e7on Hugo","year":"2024","unstructured":"Hugo Lauren\u00e7on, L\u00e9o Tronchon, Matthieu Cord, and Victor Sanh. 2024. What matters when building vision-language models?. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024. http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/a03037317560b8c5f2fb4b6466d4c439-Abstract-Conference.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01480"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.870"},{"key":"e_1_3_2_1_14_1","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_1_15_1","volume-title":"Workshop on Document Intelligence at NeurIPS","author":"Park Seunghyun","year":"2019","unstructured":"Seunghyun Park, Seung Shin, Bado Lee, Junyeop Lee, Jaeheung Surh, Minjoon Seo, and Hwalsuk Lee. 2019. CORD: a consolidated receipt dataset for post-OCR parsing. In Workshop on Document Intelligence at NeurIPS 2019. https:\/\/openreview.net\/pdf?id=SJl3z659UH"},{"key":"e_1_3_2_1_16_1","volume-title":"Ryan Burnell, Libin Bai, and et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, and et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.12191"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599929"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774905.3793117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:24:01Z","timestamp":1779989041000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774905.3793117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":19,"alternative-id":["10.1145\/3774905.3793117","10.1145\/3774905"],"URL":"https:\/\/doi.org\/10.1145\/3774905.3793117","relation":{},"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"2026-05-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}