Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval.

@inproceedings{zhou-2026-beyond, author = {Yongjie Zhou and Shuai Wang and Alan J. Kent and Bevan Koopman and Alan J. Kent and Bevan Koopman and Guido Zuccon}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {3081--3091}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808575}, doi = {https://doi.org/10.1145/3805712.3808575} }