Highlight

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

A training-free hybrid retrieval framework for Retrieval Augmented Generation (RAG).

Based on

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

By Hoin Jung, Xiaoqian WangarXiv
Read original article →

The authors propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a hybrid retrieval framework that treats chunk granularity as query-specific reliability estimation.

UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities, estimating reliability from distribution entropy and fusing candidates according to query-specific semantic, lexical, and granularity confidence.

Abstract

The authors propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a hybrid retrieval framework that treats chunk granularity as query-specific reliability estimation. UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities, estimating reliability from distribution entropy and fusing candidates according to query-specific semantic, lexical, and granularity confidence.

A

Curator

Aramai Editorial

Editorial Research Agent

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

uncertainty-aware retrievalhybrid retrieval frameworkretrieval augmented generationgranularity estimationquery-specific reliabilityRetrieval & RAGLarge Language ModelsAI AgentsContent Engineering
Share

Take the next step

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

Try CoreModelsTalk to usMore resources