Almanac
paper

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

paperactiveprovisionaluncertainty-aware-hybrid-retrieval-for-long-document-rag-612ce37c·1 events·first seen 5d ago

Aliases: Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

Co-occurring entities

More like this (12)

Recent events (1)

4arXiv · cs.CL·5d ago·source ↗

UMG-RAG: Training-free hybrid retrieval with uncertainty-aware granularity fusion for long-document RAG

Researchers propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid retrieval framework that addresses the tension between large and fine-grained retrieval chunks in RAG pipelines. The system converts dense and sparse retriever scores across multiple chunk granularities into evidence distributions, estimates reliability via entropy, and fuses candidates using query-specific confidence signals. A variant called UMGP-RAG uses fine-grained hits to locate evidence while returning broader parent chunks for coherence. Experiments on QA benchmarks show improved generation quality with no changes to the underlying retriever or generator.