{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T16:32:01Z","timestamp":1792254721436,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,27]]},"DOI":"10.1145\/3704268.3742698","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:44:47Z","timestamp":1756313087000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4383-9801","authenticated-orcid":false,"given":"Alexander","family":"Most","sequence":"first","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4592-3891","authenticated-orcid":false,"given":"Joseph","family":"Winjum","sequence":"additional","affiliation":[{"name":"Gianforte School of Computing, Montana State University, Bozeman, MT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1421-3643","authenticated-orcid":false,"given":"Manish","family":"Bhattarai","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4372-870X","authenticated-orcid":false,"given":"Shawn","family":"Jones","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3115-1226","authenticated-orcid":false,"given":"Nishath Rajiv","family":"Ranasinghe","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1741-6286","authenticated-orcid":false,"given":"Ayan","family":"Biswas","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0432-3088","authenticated-orcid":false,"given":"Dan","family":"O'Malley","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 973--983","author":"Appalaraju Srikar","unstructured":"Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, and R. Manmatha. 2021. DocFormer: End-to-End Transformer for Document Understanding. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 973--983. arXiv:2106.11539 [cs.CV]"},{"key":"e_1_3_2_1_2_1","unstructured":"Lucas Beyer Andreas Steiner Andr\u00e9 Susano Pinto Alexander Kolesnikov Xiao Wang Daniel Salz Maxim Neumann Ibrahim Alabdulmohsin Michael Tschannen Emanuele Bugliarello Thomas Unterthiner Daniel Keysers Skanda Koppula Fangyu Liu Adam Grycner Alexey Gritsenko Neil Houlsby Manoj Kumar Keran Rong Julian Eisenschlos Rishabh Kabra Matthias Bauer Matko Bo\u0161njak Xi Chen Matthias Minderer Paul Voigtlaender Ioana Bica Ivana Balazevic Joan Puigcerver Pinelopi Papalampidi Olivier Henaff Xi Xiong Radu Soricut Jeremiah Harmsen and Xiaohua Zhai. 2024. PaliGemma: A versatile 3B VLM for transfer. arXiv preprint. arXiv:2407.07726 [cs.CV]"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing. Association for Computational Linguistics","author":"Bhattarai Manish","year":"2025","unstructured":"Manish Bhattarai, Ryan Barron, Maksim E. Eren, Minh N. Vu, Vesselin Grantcharov, Ismael Ismael, Valentin Stanev, Cynthia Matuszek, Vladimir I Valtchinov, Kim Rasmussen, and Boian S. Alexandrov. 2025. HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning. In Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing. Association for Computational Linguistics, Albuquerque, New Mexic, USA, 205--214. https:\/\/aclanthology.org\/2025.knowledgenlp-1.19\/"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC62836.2024.10938485"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.knowledgenlp-1.8"},{"key":"e_1_3_2_1_6_1","volume-title":"ColPali: Efficient Document Retrieval with Vision Language Models. In The Twelfth International Conference on Learning Representations (ICLR). arXiv:2402","author":"Faysse Manuel","year":"2024","unstructured":"Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, C\u00e9line Hudelot, and Pierre Colombo. 2024. ColPali: Efficient Document Retrieval with Vision Language Models. In The Twelfth International Conference on Learning Representations (ICLR). arXiv:2402.01410 [cs.CV]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_9_1","volume-title":"Wenhao Zheng, Yiyang Zhou, Yifan Mai, Josselin Somerville Roberts, Michihiro Yasunaga, Huaxiu Yao, Cihang Xie, and Percy Liang.","author":"Lee Tony","year":"2024","unstructured":"Tony Lee, Haoqin Tu, Chi Heem Wong, Wenhao Zheng, Yiyang Zhou, Yifan Mai, Josselin Somerville Roberts, Michihiro Yasunaga, Huaxiu Yao, Cihang Xie, and Percy Liang. 2024. VHELM: A Holistic Evaluation of Vision Language Models. arXiv preprint. arXiv:2410.07112 [cs.CV]"},{"key":"e_1_3_2_1_10_1","volume-title":"Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela.","author":"Perez Ethan","year":"2020","unstructured":"PatrickLewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020). 9459--9474. arXiv:2005.11401 [cs.CL]"},{"key":"e_1_3_2_1_11_1","volume-title":"Yura Alexandr Perov, Yacine Jernite, et al.","author":"Liang Percy","year":"2022","unstructured":"Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Karan Santhanam, Jared Quincy Davis, Yura Alexandr Perov, Yacine Jernite, et al. 2022. Holistic Evaluation of Language Models. In Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_12_1","unstructured":"Bhawna Piryani Jamshid Mozafari Abdelrahman Abdallah Antoine Doucet and Adam Jatowt. 2025. MultiOCR-QA: Dataset for Evaluating Robustness of LLMs in Question Answering on Multilingual OCR Texts. arXiv preprint. arXiv:2502.16781 [cs.CL]"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning(ICML) (Proceedings of Machine Learning Research","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning(ICML) (Proceedings of Machine Learning Research, Vol. 139). PMLR, 8748--8763. arXiv:2103.00020 [cs.CV]"},{"key":"e_1_3_2_1_14_1","volume-title":"An Overview of the Tesseract OCR Engine. In ICDAR '07: Proceedings of the Ninth International Conference on Document Analysis and Recognition. IEEE Computer Society","author":"Smith Ray","year":"2007","unstructured":"Ray Smith. 2007. An Overview of the Tesseract OCR Engine. In ICDAR '07: Proceedings of the Ninth International Conference on Document Analysis and Recognition. IEEE Computer Society, Washington, DC, USA, 629--633. https:\/\/storage.googleapis.com\/pub-tools-public-publication-data\/pdf\/33418.pdf"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Zineng Tang Ziyi Yang Guoxin Wang Yuwei Fang Yang Liu Chenguang Zhu Michael Zeng Cha Zhang and Mohit Bansal. 2023. Unifying Vision Text and Layout for Universal Document Processing. In CVPR. 19254--19264.","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"e_1_3_2_1_16_1","unstructured":"Roger Waleffe Wonmin Byeon Duncan Riach Brandon Norick Vijay Korthikanti Tri Dao Albert Gu Ali Hatamizadeh Sudhakar Singh Deepak Narayanan Garvit Kulshreshtha Vartika Singh Jared Casper Jan Kautz Mohammad Shoeybi and Bryan Catanzaro. 2024. An Empirical Study of Mamba-based Language Models. arXiv preprint. arXiv:2406.07887 [cs.CL]"},{"key":"e_1_3_2_1_17_1","unstructured":"Peng Xu Wenqi Shao Kaipeng Zhang Peng Gao Shuo Liu Meng Lei Fanqing Meng Siyuan Huang Yu Qiao and Ping Luo. 2023. LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models. arXiv preprint. arXiv:2306.09265 [cs.CV]"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.211"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_21_1","unstructured":"Junyuan Zhang Qintong Zhang Bin Wang Linke Ouyang Zichen Wen Ying Li Ka-Ho Chow Conghui He and Wentao Zhang. 2024. OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation. arXiv preprint. arXiv:2412.02592 [cs.CL]"}],"event":{"name":"DocEng '25: ACM Symposium on Document Engineering 2025","location":"Nottingham United Kingdom","acronym":"DocEng '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 2025 ACM Symposium on Document Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704268.3742698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:26:32Z","timestamp":1760466392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704268.3742698"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":21,"alternative-id":["10.1145\/3704268.3742698","10.1145\/3704268"],"URL":"https:\/\/doi.org\/10.1145\/3704268.3742698","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}