Training dense retrievers for compositional sensitivity via structure-targeted negatives reduces zero-shot NanoBEIR nDCG@10 by 8-40% across backbones while only partially improving pooled-space separation of structural variants.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training for Compositional Sensitivity Reduces Dense Retrieval Generalization
Training dense retrievers for compositional sensitivity via structure-targeted negatives reduces zero-shot NanoBEIR nDCG@10 by 8-40% across backbones while only partially improving pooled-space separation of structural variants.