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.

翻译：近年来，基于嵌入的检索技术取得了显著进展，使得稠密检索器能够作为许多工业系统的核心基础设施，其中单个检索骨干网络通常被多个下游应用共享。在此类场景中，检索质量直接制约着系统性能与可扩展性，同时耦合了跨应用的模型选择、部署与回滚决策。本文针对生产级法律检索系统中作为共享骨干网络部署的检索组件，提出了实证研究结果与系统级优化方案。我们采用稠密检索器与重排序器的多阶段优化框架，并证明不同检索组件呈现出阶段依赖的权衡特性。这些观察结果促使我们采用组件级、混合阶段的配置策略，而非依赖单一的最优检查点。最终构建的骨干网络通过端到端评估验证，并已部署为支持多个工业应用的共享检索服务。