{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:07:15Z","timestamp":1784138835771,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808575","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3081-3091","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4170-288X","authenticated-orcid":false,"given":"Yongjie","family":"Zhou","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0726-5250","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5577-3391","authenticated-orcid":false,"given":"Bevan","family":"Koopman","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia and CSIRO, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-5563","authenticated-orcid":false,"given":"Guido","family":"Zuccon","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia and Google, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.845"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_1_3_1","volume-title":"Miguel Gra\u00e7a, Miguel Freire, Lei Li, and Arlindo L Oliveira.","author":"Duarte Andr\u00e9 V","year":"2024","unstructured":"Andr\u00e9 V Duarte, Jo ao DS Marques, Miguel Gra\u00e7a, Miguel Freire, Lei Li, and Arlindo L Oliveira. 2024. Lumberchunker: Long-form narrative document segmentation. In Findings of the Association for Computational Linguistics: EMNLP 2024. 6473-6486."},{"key":"e_1_3_2_1_4_1","volume-title":"Bo Wang, and Han Xiao.","author":"G\u00fcnther Michael","year":"2024","unstructured":"Michael G\u00fcnther, Isabelle Mohr, Daniel James Williams, Bo Wang, and Han Xiao. 2024. Late chunking: contextual chunk embeddings using long-context embedding models. arXiv preprint arXiv:2409.04701 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, Maximilian Werk, Nan Wang, and Han Xiao.","author":"G\u00fcnther Michael","year":"2023","unstructured":"Michael G\u00fcnther, Jackmin Ong, Isabelle Mohr, Alaeddine Abdessalem, Tanguy Abel, Mohammad Kalim Akram, Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, Maximilian Werk, Nan Wang, and Han Xiao. 2023. Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents. arXiv preprint arXiv:2310.19923 (2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"Greg Kamradt. 2024. Levels of Text Splitting. https:\/\/github.com\/FullStackRetrieval-com\/RetrievalTutorials\/tree\/main\/tutorials\/LevelsOfTextSplitting. Accessed: 2026-02-09."},{"key":"e_1_3_2_1_7_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_8_1","volume-title":"A survey of generative search and recommendation in the era of large language models. arXiv preprint arXiv:2404.16924","author":"Li Yongqi","year":"2024","unstructured":"Yongqi Li, Xinyu Lin, Wenjie Wang, Fuli Feng, Liang Pang, Wenjie Li, Liqiang Nie, Xiangnan He, and Tat-Seng Chua. 2024. A survey of generative search and recommendation in the era of large language models. arXiv preprint arXiv:2404.16924 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_2_1_10_1","volume-title":"Nomic embed: Training a reproducible long context text embedder. arXiv preprint arXiv:2402.01613","author":"Nussbaum Zach","year":"2024","unstructured":"Zach Nussbaum, John X Morris, Brandon Duderstadt, and Andriy Mulyar. 2024. Nomic embed: Training a reproducible long context text embedder. arXiv preprint arXiv:2402.01613 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, and Han Xiao.","author":"Sturua Saba","year":"2024","unstructured":"Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, and Han Xiao. 2024. jina-embeddings-v3: Multilingual Embeddings With Task LoRA. arXiv preprint arXiv:2409.10173 (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"Nandan Thakur Nils Reimers Andreas R\u00fcckl\u00e9 Abhishek Srivastava and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ"},{"key":"e_1_3_2_1_13_1","volume-title":"Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672","author":"Wang Liang","year":"2024","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024b. Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657853"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 4106-4109","author":"Zuccon Guido","year":"2025","unstructured":"Guido Zuccon, Shengyao Zhuang, and Xueguang Ma. 2025. R2LLMs: Retrieval and Ranking with LLMs. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 4106-4109."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:25:13Z","timestamp":1784136313000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808575"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":15,"alternative-id":["10.1145\/3805712.3808575","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808575","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}