Constructing Hard-Positive Query-Document Pairs for Dense Retrieval via Phrase Representativeness.

@inproceedings{wu-2026-constructing, author = {Zhanyu Wu and Michael Huggett and Richong Zhang and Michael Huggett and Richong Zhang and Zhijie Nie}, 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 = {{Constructing Hard-Positive Query-Document Pairs for Dense Retrieval via Phrase Representativeness}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {2005--2014}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809734}, doi = {https://doi.org/10.1145/3805712.3809734} }