Why Knowledge Distillation Fails to Scale in Neural Retrieval.

@inproceedings{zuccon-2026-knowledge, author = {Guido Zuccon and Shu Zhou and Graham McDonald and Tao Fan and Rui Ling and Craig Macdonald and Hao Wang and Junan Chen and Graham McDonald and Tao Fan and Guido Zuccon and Shu Zhou and Craig Macdonald and Hao Wang}, 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 = {{Why Knowledge Distillation Fails to Scale in Neural 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 = {4397--4402}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809985}, doi = {https://doi.org/10.1145/3805712.3809985} }