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-compress local relevance signals, while token-level late interaction retains every tokenizer subword at…
Thank you for reading this post, don't forget to subscribe!
Source: cs.AI updates on arXiv.org
Automatically aggregated summary — full article and all rights belong to the original publisher.