paper
Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
paperactiveprovisional
uncertainty-aware-hybrid-retrieval-for-long-document-rag-612ce37c·1 events·first seen 5d agoAliases: Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
Co-occurring entities
More like this (12)
Uncertainty-aware Multi-Granularity RAGhybrid dense-sparse retrievalRetrieval-Augmented GenerationTrace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question AnsweringUnderstanding the Behaviors of Environment-aware Information RetrievalWhen Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense RetrievalContextual RetrievalUncertainty QuantificationAttention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized EmbeddingsSelf-Augmenting Retrieval for Diffusion Language ModelsDifference-Aware Retrieval Policies for Imitation LearningAttention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It
Recent events (1)
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.