提出可扩展的多样性检索方法，兼顾相关性与多样性。
Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming
- 将多样性检索建模为带基数约束的二元二次规划问题。
- 在多个数据集上优于基线，在相关性与多样性权衡中表现更优。
- 适合需要高效高质检索的生成式应用，如RAG系统。
多样性感知检索对检索增强生成（RAG）至关重要，但现有方法缺乏理论保障且随检索段落数 $k$ 增大时可扩展性差。本文将多样性检索形式化为基数约束的二元二次规划（CCBQP），通过可解释的权衡参数显式平衡相关性与语义多样性。受组合优化最新进展启发，提出非凸紧连续松弛及基于Frank--Wolfe的算法，并提供景观分析与收敛性保证。大量实验表明，该方法在相关性-多样性帕累托前沿上持续优于基线，同时实现显著加速。
原文摘要 · Abstract (English)
Diversity-aware retrieval is essential for Retrieval-Augmented Generation (RAG), yet existing methods lack theoretical guarantees and face scalability issues as the number of retrieved passages $k$ increases. We propose a principled formulation of diversity retrieval as a cardinality-constrained binary quadratic programming (CCBQP), which explicitly balances relevance and semantic diversity through an interpretable trade-off parameter. Inspired by recent advances in combinatorial optimization, we develop a non-convex tight continuous relaxation and a Frank--Wolfe based algorithm with landscape analysis and convergence guarantees. Extensive experiments demonstrate that our method consistently dominates baselines on the relevance-diversity Pareto frontier, while achieving significant speedup.
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。