让大模型在不重训的情况下，实时用新文档做检索。
ICICLE: Expanding Retrieval with In-Context Documents
- 用上下文提供新文档信息，不更新模型参数即可扩展知识库。
- 在MS MARCO和NQ320K上新文档召回率提升，旧文档记忆保持不变。
- 适合需要快速扩容、避免重训练的实时检索系统使用。
生成式检索（GR）通过参数化知识将查询直接映射到文档标识符（docids），但新增文档需重新训练模型以编码新关联，成本高且易遗忘旧知识。本文将增量式生成式检索重构为上下文检索问题：新文档作为推理时的证据输入。提出ICICLE框架，基于参数记忆与上下文提供的文档-标识对，实现源感知的docid生成。该方法结合[COPY]路由机制、偏好校准与大上下文适配，区分上下文依赖检索与参数化检索。在MS MARCO和NQ320K上的实验表明，ICICLE在不进行特定语料重训练的前提下，提升了新文档的检索效果，同时保留了已见文档的召回能力。分析显示，高样本退化主要源于路由失败，凸显源选择校准是扩展上下文生成检索的关键瓶颈。
原文摘要 · Abstract (English)
Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to encode new document-docid associations incurs repeated training and catastrophic forgetting of previously indexed documents. In this work, we revisit incremental GR as an in-context retrieval problem, where newly added documents are supplied as inference-time document-docid evidence. We propose ICICLE, an in-context indexing framework that performs source-aware docid generation over both parametric memory and context-provided document-docid pairs. ICICLE combines a `[COPY]`-based routing mechanism, preference-based calibration, and large context adaptation to distinguish context-grounded retrieval from parametric retrieval. Experiments on MS MARCO and NQ320K show that ICICLE improves retrieval of newly introduced documents while preserving seen-document retention without corpus-specific retraining. Our analysis further shows that high-shot degradation is mainly caused by routing failure, highlighting source-selection calibration as a key bottleneck for scaling in-context generative retrieval.
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。