Rescaling the MLM-head projection by a constant factor at initialization resolves scale mismatch in learned sparse retrieval and enables stable use of large-norm backbones such as ModernBERT.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.IR 4years
2026 4representative citing papers
ColBERTSaR uses product quantization on ColBERT embeddings to create a true inverted index that is 50-70% smaller than one-bit PLAID while retaining retrieval effectiveness, and is theoretically equivalent to learned-sparse retrieval except for scoring.