A Unified Structured Query Understanding Framework for Industrial Semantic Search
For industrial search systems, this work reduces maintenance overhead and improves consistency, especially for long-tail queries, by consolidating multiple components into a single model.
LinkedIn deployed a unified Small Language Model (SLM) for query understanding in job search, replacing a cascade of task-specific components. The system improved user engagement and reduced operational costs while meeting strict latency constraints on limited GPU resources.
Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components. While individually optimizable, this fragmented architecture incurs high maintenance overhead and results in inconsistent behaviors, particularly for long-tail queries. In this work, we propose and deploy a unified structured query understanding system that consolidates these heterogeneous functions into a single Small Language Model (SLM) that performs schema-constrained generation. To address the data bottlenecks inherent in unified modeling, we introduce Query Illuminator, a dual-purpose framework serving as: (i) a teacher model for high-quality auto-annotation and distillation, and (ii) a surrogate judge for scalable evaluation where human labels are scarce. We validate this approach through extensive offline and online tests within LinkedIn's Job Search system. Furthermore, we demonstrate the framework's horizontal extensibility through a cross-domain case study on People Search. The results show improved user engagement and reduced operational costs, achieved while satisfying strict low-latency serving constraints on limited GPU resources.