让检索系统自动适应新数据流，无需标签也能持续提升效果。
CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory
- 用动态软记忆存储数据流语义变化，支持持续学习。
- 在无标签环境下，成功@5提升27.79%，召回率@10提升44.5%。
- 适合需要长期更新、无标注数据的实时检索场景。
动态数据流中的信息检索是关键任务，因数据分布漂移会降低AI检索系统性能。现有基于记忆的持续学习方法依赖固定查询与真实文档，限制了对未见数据的泛化能力，难以应用于真实场景。为此，我们提出CREAM，一种基于记忆的自监督持续检索框架。CREAM将流式查询与文档的语义演化捕捉到动态结构化的软记忆中，并在无监督设置下适应已见与未见主题。通过细粒度相似性估计、正则化聚类原型构建和分层核样本采样三项技术实现。在两个基准数据集上的实验表明，CREAM展现出更强适应性与检索准确率，在无标签设置下平均优于最强基线27.79%（Success@5）和44.5%（Recall@10），性能达到甚至超过有监督方法水平。
原文摘要 · Abstract (English)
Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been widely adopted for IR. However, existing methods rely on a fixed set of queries with ground-truth documents, which limits generalization to unseen data, making them impractical for real-world applications. To enable more effective learning with unseen topics of a new corpus without ground-truth labels, we propose CREAM, a self-supervised framework for memory-based continual retrieval. CREAM captures the evolving semantics of streaming queries and documents into dynamically structured soft memory and leverages it to adapt to both seen and unseen topics in an unsupervised setting. We realize this through three key techniques: fine-grained similarity estimation, regularized cluster prototyping, and stratified coreset sampling. Experiments on two benchmark datasets demonstrate that CREAM exhibits superior adaptability and retrieval accuracy, outperforming the strongest method in a label-free setting by 27.79% in Success@5 and 44.5% in Recall@10 on average, and achieving performance comparable to or even exceeding that of supervised methods.
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。