LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum.

Zhichao Xu|Shengyao Zhuang|Crystina Zhang|Xueguang Ma|Yijun Tian|Maitrey Mehta|Jimmy Lin|Vivek Srikumar


Anthology ID:DBLP:conf/sigir/XuZZMTMLS26
Volume:Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026
Year:2026
Venue:Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
Publisher:ACM
Pages:4298-4304
URL:https://doi.org/10.1145/3805712.3809869
DOI:https://doi.org/10.1145/3805712.3809869
DBLP:conf/sigir/XuZZMTMLS26
BibTeX:
@inproceedings{xu-2026-laconic, author = {Zhichao Xu and Shengyao Zhuang and Crystina Zhang and Xueguang Ma and Yijun Tian and Maitrey Mehta and Jimmy Lin and Vivek Srikumar}, 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 = {{LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {4298--4304}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809869}, doi = {https://doi.org/10.1145/3805712.3809869} }