arXiv cs.AI
· Papers
H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases
arXiv:2608.00065v3 Announce Type: replace Abstract: Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing representations lie at two extremes: single-vector retrievers often over-com