Saved in:
Bibliographic Details
Main Authors: Lu, Qiheng, Sidiropoulos, Nicholas D.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.02554
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910099242483712
author Lu, Qiheng
Sidiropoulos, Nicholas D.
author_facet Lu, Qiheng
Sidiropoulos, Nicholas D.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02554
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming
Lu, Qiheng
Sidiropoulos, Nicholas D.
Computation and Language
Information Retrieval
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.
title Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2604.02554