不确定性感知的混合检索用于长文档RAG
Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
AI总结：
提出UMG-RAG，一种无需训练的混合检索框架，通过多粒度分块和不确定性估计融合密集与稀疏检索结果，提升长文档问答质量。
摘要：
检索增强生成（RAG）关键依赖于检索证据的质量和粒度。大的检索单元保留上下文但常引入无关内容，可能稀释答案承载证据并恶化长上下文利用。细粒度单元更紧凑，但可能难以可靠检索，因为短块可能缺乏匹配查询所需的语义、词汇或桥接线索。我们提出不确定性感知的多粒度RAG（UMG-RAG），一种无需训练的混合检索框架，将分块粒度视为查询特定的可靠性估计。UMG-RAG不训练新检索器或修改生成器，而是利用现有密集和稀疏检索器作为跨多个分块粒度的互补专家。对于每个查询，它将每个专家-粒度得分列表转换为证据分布，从分布熵估计可靠性，并根据查询特定的语义、词汇和粒度置信度融合候选。我们进一步引入UMGP-RAG，一种父级提升变体，利用细粒度命中定位相关证据，同时返回更广泛的非冗余父块以保持局部连贯性。在问答基准上的实验表明，不确定性感知融合和父级提升在保持轻量级、即插即用检索管道的同时，提高了生成质量。
英文摘要：
Retrieval augmented generation (RAG) depends critically on the quality and granularity of retrieved evidence. Large retrieval units preserve context but often introduce irrelevant content, which can dilute answer bearing evidence and worsen long context utilization. Fine-grained units are more compact, but they may be difficult to retrieve reliably because short chunks can lack semantic, lexical, or bridging cues needed to match the query. We propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid retrieval framework that treats chunk granularity as query-specific reliability estimation. Instead of training a new retriever or modifying the generator, UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities. For each query, it converts each expert-granularity score list into an evidence distribution, estimates reliability from distribution entropy, and fuses candidates according to query-specific semantic, lexical, and granularity confidence. We further introduce UMGP-RAG, a parent promotion variant that uses fine-grained hits to locate relevant evidence while returning broader non-redundant parent chunks for local coherence. Experiments on question answering benchmarks show that uncertainty-aware fusion and parent promotion improve generation quality while maintaining a lightweight, plug-and-play retrieval pipeline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
