A learned router for a dual-mode LLM raises medical QA accuracy from 0.827 to 0.839 while cutting inference time by 36.8% and tokens by 39.7% versus always using thinking mode.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model
A learned router for a dual-mode LLM raises medical QA accuracy from 0.827 to 0.839 while cutting inference time by 36.8% and tokens by 39.7% versus always using thinking mode.