BoundaryMORPH：通过主动集合选择进行预算受限的重排序以应对弥散检索
BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval
浏览论文内容
中文总结 AI 辅助
针对弥散检索中CE预算小于上下文容量的不匹配问题，提出BoundaryMORPH算法，利用高斯过程将CE预算用于边界处top-k集合成员判定，实现最先进的集合检索质量。
中文摘要 AI 辅助
现代检索增强生成（RAG）中的开放式查询日益“弥散”，需要将大量文档组装到有限的LLM上下文窗口中。为确保检索质量，系统使用快速的双编码器和更昂贵的交叉编码器（CE）对候选文档进行评分。然而，CE预算B严格受延迟限制，且通常小于上下文窗口容量k。这种不匹配使得标准重排序在结构上存在缺陷：它浪费计算资源验证明显靠前的候选文档，而忽略了初始排名中较靠后的相关文档。为解决此问题，我们提出BoundaryMORPH，一种新颖的算法，专门为LLM的上下文容量k分配CE预算。利用高斯过程，BoundaryMORPH将初始双编码器排名视为结构先验，并智能地将CE调用用于解决边界处的top-k集合成员资格问题，而非寻找单个最相关文档。每次CE调用的信息会传播到未评分的文档，从而最大化预算效用。我们证明，在多个模型和开放式查询数据集上，BoundaryMORPH实现了最先进的集合检索质量（相较于最强基线，nCG@100提升+5.4）。
英文摘要
Open-ended queries in modern Retrieval-Augmented Generation (RAG) are increasingly "diffuse," requiring a large set of documents to be assembled into a finite LLM context window. To ensure retrieval quality, systems use fast dual-encoders and more expensive cross-encoders (CEs) to score candidates. However, the CE budget $B$ is strictly bounded by latency and is often smaller than the context window capacity $k$. This mismatch makes standard reranking structurally flawed: it wastes compute verifying obvious top candidates while ignoring relevant documents further down the initial ranking. To address this, we introduce BoundaryMORPH, a novel algorithm that allocates CE budget specifically for the LLM's context capacity $k$. Using a Gaussian Process, BoundaryMORPH treats the initial dual-encoder ranking as a structural prior and intelligently spends CE calls on resolving top-$k$ set membership at the boundary, rather than seeking a single most-relevant document. Information from each CE call propagates to unscored documents, maximizing the utility of the budget. We demonstrate that BoundaryMORPH achieves state-of-the-art set retrieval quality across multiple models and datasets with open-ended queries ($+5.4$ nCG@100 over the strongest baseline).
发表机构
- Purdue University（普渡大学）
- AWS AI Labs（亚马逊AI实验室）
机构由 AI 辅助整理，请以论文原文为准。
