系统梳理检索框架设计陷阱与范式，助你平衡效率与效果。
Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms
- 从表征、粒度到编排、鲁棒性，分层解析检索系统设计
- 提出多级分块、多阶段重排序等方法缓解长文本信息瓶颈
- 适合想优化搜索系统性能的研究者和工程师参考
构建嵌入检索系统需权衡效率与效果之间的复杂矛盾。本文将这些设计决策结构化为系统设计栈的垂直遍历。首先在表征层分析损失函数与架构（如双编码器和交叉编码器）如何定义语义相关性与几何投影；其次在粒度层评估原子式与层级式分块策略对长文档信息瓶颈的缓解作用；接着在编排层探讨超越单向量范式的方案，包括层级检索、代理分解和多阶段重排序流水线以突破容量限制；最后在鲁棒性层识别针对领域泛化失败、词汇盲区及时间漂移导致的检索质量无声退化的架构应对策略。通过分类归纳这些局限与设计选择，为从业者提供优化现代神经搜索系统效率-效果边界的综合框架。
原文摘要 · Abstract (English)
Designing an embedding retrieval system requires navigating a complex design space of conflicting trade-offs between efficiency and effectiveness. This work structures these decisions as a vertical traversal of the system design stack. We begin with the Representation Layer by examining how loss functions and architectures, specifically Bi-encoders and Cross-encoders, define semantic relevance and geometric projection. Next, we analyze the Granularity Layer and evaluate how segmentation strategies like Atomic and Hierarchical chunking mitigate information bottlenecks in long-context documents. Moving to the Orchestration Layer, we discuss methods that transcend the single-vector paradigm, including hierarchical retrieval, agentic decomposition, and multi-stage reranking pipelines to resolve capacity limitations. Finally, we address the Robustness Layer by identifying architectural mitigations for domain generalization failures, lexical blind spots, and the silent degradation of retrieval quality due to temporal drift. By categorizing these limitations and design choices, we provide a comprehensive framework for practitioners to optimize the efficiency-effectiveness frontier in modern neural search systems.
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。