Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference
Signed Rescue Routing improves LLM cascade efficiency by predicting when a larger model actually corrects a smaller one rather than uncertainty.
1 stories, newest first · one card per story
Signed Rescue Routing improves LLM cascade efficiency by predicting when a larger model actually corrects a smaller one rather than uncertainty.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views