用可自适应的检索器组合提升问答系统性能与效率
Retriever Portfolios: A Principled Approach to Adaptive RAG
- 从多个检索器中自动选优组成组合，覆盖不同查询类型
- 在多基准测试中优于单检索器和简单多检索器方案
- 固定组合支持并行处理，提速降耗且效果更稳
检索增强生成（RAG）系统通常依赖单一检索器和一组固定超参数，但面对从简单事实到复杂多跳推理等多样化的查询时表现受限。本文提出一种方法，能从大量候选检索器中自动选取一个小型、多样化的组合（即检索器组合），以覆盖目标查询分布的不同区域。通过在查询分布上定义期望最优的‘最佳k个’目标，证明该设定可导出具有近似最优保证的高效组合构建算法。在多个问答基准测试中，所学得的组合与路由管道在检索指标和答案质量上均持续优于单检索器及朴素多检索器基线。相比运行时超参数调优，固定组合支持并行检索与大模型调用，在保持相当（甚至更优）准确率的同时，显著降低延迟与令牌消耗。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) systems typically rely on a single retriever and a single set of hyperparameters, despite facing highly heterogeneous queries that range from simple factoid questions to complex multi-hop reasoning. We propose a method that automatically selects a small, diverse subset of retrievers (a portfolio) from a large pool of candidates, to cover different regions of the target query distribution. We formalize this setting via an expected best-of-$k$ objective over the query distribution and show that it admits an efficient portfolio construction algorithm with near-optimal guarantees. Across multiple QA benchmarks, our learned portfolios and router pipeline consistently outperform single-retriever and naive multi-retriever baselines on both retrieval metrics and answer quality. In addition, compared to inference-time hyperparameter tuning approaches, fixed portfolios enable parallel retrieval and LLM calls, achieving comparable (and sometimes better) accuracy with substantially lower latency and token cost.
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。