优化检索生成中的证据集选择与排序，提升生成质量与效率
OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation
- 采用先扩展后精炼的框架，生成多样化候选集并压缩冗余
- 通过自合成策略无监督构建偏好标签，识别互补与重复证据
- 联合优化集合选择与集合级排序，更高效地生成高质量回答
检索增强生成（RAG）通过从大规模外部语料中检索证据来提升生成质量。然而，现有方法多依赖静态选取相关性最高的前k条文本，忽视了文本间的组合增益，常引入大量冗余信息。为此，本文提出OptiSet，一种以集合为中心的统一框架，实现证据集选择与集合级排序的协同优化。该框架采用“扩展-精炼”范式：首先将查询扩展为多个视角，生成多样化的候选集；再通过重新筛选形成紧凑的证据集。随后，设计无需强大语言模型监督的自合成策略，基于生成器在不同证据集条件下的效用变化，自动构建偏好标签，从而识别互补与冗余证据。最后，引入集合-列表联合训练策略，同时优化集合选择与集合级排序，使模型倾向于选择紧凑且高收益的证据集。大量实验表明，OptiSet在复杂组合问题上显著提升性能，并提高生成效率。代码已开源。
原文摘要 · Abstract (English)
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.
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。