SOURCE-LINKED INTELLIGENCE

Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Large language model (LLM) cascades answer easy requests with a small model and escalate selected requests to a larger model. Most routers prioritize examples on which the small model appears uncertain or likely to be wrong. This proxy ignores a decisive fact: escalation is useful only when the large model corrects the small model, and it is harmful when the large model replaces a correct answer with an incorrect one. We introduce Signed Rescue Routing (SRR), a budgeted routing method that predicts these two events separately and ranks requests by their difference. We show that this signed con

Read original source ↗ Open in workspace

recordType

paper

region

Global