针对共享主干的检索系统，提出分组件多阶段优化方法
Optimizing Retrieval Components for a Shared Backbone via Component-Wise Multi-Stage Training
- 按组件分别设计多阶段训练策略，避免统一模型限制
- 实测不同组件在不同阶段表现各异，需差异化配置
- 已在生产级法律检索系统落地，支持多业务共用
基于嵌入的检索技术已广泛应用于工业系统中，多个下游应用常共享同一检索主干。在此场景下，检索质量直接决定系统性能与可扩展性，且模型选择、部署与回滚决策相互耦合。本文针对生产环境中的法律检索系统，提出一种面向共享主干的检索组件优化方案。通过采用多阶段优化框架对稠密检索器与重排序器进行训练，发现不同检索组件存在阶段依赖的性能权衡。这一发现促使我们采用分组件、混合阶段的配置策略，而非依赖单一最优检查点。最终构建的共享检索主干经过端到端评估验证，并成功部署为支撑多个工业应用的统一服务。
原文摘要 · Abstract (English)
Recent advances in embedding-based retrieval have enabled dense retrievers to serve as core infrastructure in many industrial systems, where a single retrieval backbone is often shared across multiple downstream applications. In such settings, retrieval quality directly constrains system performance and extensibility, while coupling model selection, deployment, and rollback decisions across applications. In this paper, we present empirical findings and a system-level solution for optimizing retrieval components deployed as a shared backbone in production legal retrieval systems. We adopt a multi-stage optimization framework for dense retrievers and rerankers, and show that different retrieval components exhibit stage-dependent trade-offs. These observations motivate a component-wise, mixed-stage configuration rather than relying on a single uniformly optimal checkpoint. The resulting backbone is validated through end-to-end evaluation and deployed as a shared retrieval service supporting multiple industrial applications.
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。