Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.05027 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917190714785792 |
|---|---|
| author | Jiang, Yi Zhao, Sendong Li, Jianbo Hu, Bairui Du, Yanrui Wang, Haochun Qin, Bing |
| author_facet | Jiang, Yi Zhao, Sendong Li, Jianbo Hu, Bairui Du, Yanrui Wang, Haochun Qin, Bing |
| contents | Retrieval-Augmented Generation (RAG) improves generation quality by incorporating evidence retrieved from large external corpora. However, most existing methods rely on statically selecting top-k passages based on individual relevance, which fails to exploit combinatorial gains among passages and often introduces substantial redundancy. To address this limitation, we propose OptiSet, a set-centric framework that unifies set selection and set-level ranking for RAG. OptiSet adopts an "Expand-then-Refine" paradigm: it first expands a query into multiple perspectives to enable a diverse candidate pool and then refines the candidate pool via re-selection to form a compact evidence set. We then devise a self-synthesis strategy without strong LLM supervision to derive preference labels from the set conditional utility changes of the generator, thereby identifying complementary and redundant evidence. Finally, we introduce a set-list wise training strategy that jointly optimizes set selection and set-level ranking, enabling the model to favor compact, high-gain evidence sets. Extensive experiments demonstrate that OptiSet improves performance on complex combinatorial problems and makes generation more efficient. The source code is publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05027 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation Jiang, Yi Zhao, Sendong Li, Jianbo Hu, Bairui Du, Yanrui Wang, Haochun Qin, Bing Artificial Intelligence Retrieval-Augmented Generation (RAG) improves generation quality by incorporating evidence retrieved from large external corpora. However, most existing methods rely on statically selecting top-k passages based on individual relevance, which fails to exploit combinatorial gains among passages and often introduces substantial redundancy. To address this limitation, we propose OptiSet, a set-centric framework that unifies set selection and set-level ranking for RAG. OptiSet adopts an "Expand-then-Refine" paradigm: it first expands a query into multiple perspectives to enable a diverse candidate pool and then refines the candidate pool via re-selection to form a compact evidence set. We then devise a self-synthesis strategy without strong LLM supervision to derive preference labels from the set conditional utility changes of the generator, thereby identifying complementary and redundant evidence. Finally, we introduce a set-list wise training strategy that jointly optimizes set selection and set-level ranking, enabling the model to favor compact, high-gain evidence sets. Extensive experiments demonstrate that OptiSet improves performance on complex combinatorial problems and makes generation more efficient. The source code is publicly available. |
| title | OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.05027 |