Adaptive Re-Ranking trains a classifier to route queries to BM25, MiniLM-L6-v2, or BGE-v2-m3 based on a utility label, yielding 1.15-53x lower median latency and competitive nDCG@10 versus always using the heaviest model.
Bruce Croft
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A unified SLM framework with schema-constrained generation replaces cascaded query understanding components, using Query Illuminator for auto-annotation and evaluation, deployed on LinkedIn Job Search with reported gains in engagement and cost reduction.
citing papers explorer
-
Adaptive Re-Ranking
Adaptive Re-Ranking trains a classifier to route queries to BM25, MiniLM-L6-v2, or BGE-v2-m3 based on a utility label, yielding 1.15-53x lower median latency and competitive nDCG@10 versus always using the heaviest model.
-
A Unified Structured Query Understanding Framework for Industrial Semantic Search
A unified SLM framework with schema-constrained generation replaces cascaded query understanding components, using Query Illuminator for auto-annotation and evaluation, deployed on LinkedIn Job Search with reported gains in engagement and cost reduction.