BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval

2026-09-22

AI Summary

为解决检索增强生成中因预算限制导致的重排序问题，BoundaryMORPH算法通过高斯过程智能分配交叉编码器预算，以优化前k个文档的选择。

Abstract

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).

Problem

• Retrieval-Augmented Generation
• diffuse queries
• cross-encoders budget
• context window capacity
• reranking

Innovation

• BoundaryMORPH
• Gaussian Process
• budget allocation
• set retrieval
• cross-encoders