RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2verdicts
CONDITIONAL 2representative citing papers
LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.
citing papers explorer
-
Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
-
LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations
LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.