Pre-inference routing saves cost only when many documents are hard for the cheap model and those hard cases are visible in document features; a pilot test identifies such genres, with 31-77% savings where both hold.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pre-Inference Routing for Cost-Efficient Document Field Extraction
Pre-inference routing saves cost only when many documents are hard for the cheap model and those hard cases are visible in document features; a pilot test identifies such genres, with 31-77% savings where both hold.