用混合检索器动态匹配不同查询，效果超越单一模型。
MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers
- 零样本融合稀疏、稠密与人类检索器，按需加权组合。
- 仅0.8B参数，平均比单个检索器高10.8%，超7B模型3.9%。
- 可整合真人知识源，相对模拟人类提升58.9%性能。
检索增强生成（RAG）的效果高度依赖于所用检索器及其使用方式。不同检索器提供互补信号：BM25捕捉词汇匹配，稠密检索器捕捉语义相似性。但实践中通常基于经验固定单一检索器，难以应对多样化信息需求。本文通过量化分析验证该直觉，提出混合检索器——一种零样本的异构检索器加权组合方法。大量实验表明，此类混合方法高效有效：尽管总参数量仅为0.8B，其在平均表现上仍优于所有独立检索器，且相较7B大模型提升3.9%。进一步分析显示，该框架可有效整合非理想的人类信息源作为检索器，实现良好协作，性能相比仅使用模拟人类提升58.9%。
原文摘要 · Abstract (English)
Retrieval-augmented Generation (RAG) is powerful, but its effectiveness hinges on which retrievers we use and how. Different retrievers offer distinct, often complementary signals: BM25 captures lexical matches; dense retrievers, semantic similarity. Yet in practice, we typically fix a single retriever based on heuristics, which fails to generalize across diverse information needs. Can we dynamically select and integrate multiple retrievers for each individual query, without the need for manual selection? In our work, we validate this intuition with quantitative analysis and introduce mixture of retrievers: a zero-shot, weighted combination of heterogeneous retrievers. Extensive experiments show that such mixtures are effective and efficient: Despite totaling just 0.8B parameters, this mixture outperforms every individual retriever and even larger 7B models by +10.8% and +3.9% on average, respectively. Further analysis also shows that this mixture framework can help incorporate specialized non-oracle human information sources as retrievers to achieve good collaboration, with a 58.9% relative performance improvement over simulated humans alone.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。