Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.03240 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913003946901504 |
|---|---|
| author | Sun, Xun Xie, Baiheng Huang, Li Gao, Qiang |
| author_facet | Sun, Xun Xie, Baiheng Huang, Li Gao, Qiang |
| contents | Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge, yielding relevance responses that are aligned with factual evidence and evolving corpora. Standard RAG pipelines construct context through relevance ranking, performing point-wise scoring between the user query and each corpora chunk. This formulation, however, ignores interactions among retrieved candidates, leading to redundant contexts that dilute density and fail to surface complementary evidence. We argue that effective retrieval should optimize jointly for both density and diversity, ensuring the grounding evidence that is dense in information yet diverse in coverage. In this study, we propose ScalDPP, a diversity-aware retrieval mechanism for RAG that incorporates Determinantal Point Processes (DPPs) through a lightweight P-Adapter, enabling scalable modeling of inter-chunk dependencies and complementary context selection. In addition, we develop a novel set-level objective, Diverse Margin Loss (DML), that enforces ground-truth complementary evidence chains to dominate any equally sized redundant alternatives under DPP geometry. Experimental results demonstrate the superiority of ScalDPP, substantiating our core statement in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03240 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scaling DPPs for RAG: Density Meets Diversity Sun, Xun Xie, Baiheng Huang, Li Gao, Qiang Machine Learning Artificial Intelligence Computation and Language Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge, yielding relevance responses that are aligned with factual evidence and evolving corpora. Standard RAG pipelines construct context through relevance ranking, performing point-wise scoring between the user query and each corpora chunk. This formulation, however, ignores interactions among retrieved candidates, leading to redundant contexts that dilute density and fail to surface complementary evidence. We argue that effective retrieval should optimize jointly for both density and diversity, ensuring the grounding evidence that is dense in information yet diverse in coverage. In this study, we propose ScalDPP, a diversity-aware retrieval mechanism for RAG that incorporates Determinantal Point Processes (DPPs) through a lightweight P-Adapter, enabling scalable modeling of inter-chunk dependencies and complementary context selection. In addition, we develop a novel set-level objective, Diverse Margin Loss (DML), that enforces ground-truth complementary evidence chains to dominate any equally sized redundant alternatives under DPP geometry. Experimental results demonstrate the superiority of ScalDPP, substantiating our core statement in practice. |
| title | Scaling DPPs for RAG: Density Meets Diversity |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.03240 |