Saved in:
| Main Authors: | , |
|---|---|
| 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 |