Highlight

SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context

A training-free routing framework for knowledge graph retrieval-augmented generation.

Based on

SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context

By Wang, Hairu, Yuan Feng, Yukun Cao, Xie, Xike, S Kevin ZhouarXiv (Cornell University)
Read original article →

The authors propose a simple and effective routing framework, SkewRoute, which balances performance and cost in knowledge graph retrieval-augmented generation. The framework is designed to direct queries to the most suitable language models based on score skewness of retrieved contexts.

It achieves over 3x higher routing effectiveness while reducing runtime compared to existing methods.

Abstract

The authors propose a simple and effective routing framework, SkewRoute, which balances performance and cost in knowledge graph retrieval-augmented generation. The framework is designed to direct queries to the most suitable language models based on score skewness of retrieved contexts. It achieves over 3x higher routing effectiveness while reducing runtime compared to existing methods.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

skewroutellm routingknowledge graph retrieval-augmented generationtraining-free frameworkperformance and cost balanceKnowledge GraphsRetrieval & RAGLarge Language ModelsContent Engineering
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources
SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context | Aramai