通过用户聚类提升个性化生成，降低检索成本并增强效果。
ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
- 用用户文档聚类，基于相似性筛选相关资料
- 在多个任务上超越现有方法，提升生成质量
- 兼容不同检索器与语言模型，适合实际应用
个性化检索增强生成（RAG）依赖于精准选择用户相关的文档。现有方法常面临高检索开销，且忽略相似用户间的协同信号对当前用户生成的促进作用。本文提出 ClusterRAG，一种基于聚类的协同过滤个性化检索增强生成方法。ClusterRAG通过用户画像文档表征用户，采用基于密度的聚类算法将用户组织成语义一致的簇，并在簇级和文档级进行检索，分别利用簇级相似性和细粒度排序。在 LaMP 基准上的大量实验表明，联合使用目标用户及其最相似用户的画像文档，在多种任务中均实现最优性能。进一步分析显示，ClusterRAG 可无缝适配不同密集检索器与排序器，且在微调和零样本语言模型下仍保持有效性。
原文摘要 · Abstract (English)
Personalized Retrieval-Augmented Generation (RAG) relies on accurately selecting user-relevant documents. In practice, existing RAG approaches often suffer from high retrieval costs and overlook that collaborative signals from similar users can enhance personalized generation for the current user. We propose ClusterRAG, a Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation. ClusterRAG represents users through their profile documents, organizes users into semantically coherent clusters using density-based clustering, and performs retrieval at both the cluster and document levels via cluster-level similarity and fine-grained ranking. Extensive experiments on the LaMP benchmark demonstrate that jointly leveraging the target user's profile and profiles from top similar users consistently yields the best performance across diverse tasks. Further analysis shows that ClusterRAG integrates seamlessly with different dense retrievers and rankers, and remains effective when paired with both fine-tuned and zero-shot language models.
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。