Policy-Grounded Dynamic Facet Suggestions for Job Search
For job seekers on LinkedIn, this system addresses the challenge of underspecified queries by providing real-time personalized suggestions to disambiguate intent.
LinkedIn's dynamic facet suggestion system for job search, using a policy-grounded retrieval-augmented ranking framework with a distilled small language model, improved suggestion engagement and job search outcomes in online A/B tests.
Job seekers often initiate search with short, underspecified queries. At LinkedIn, over 80% of job-related queries contain three or fewer keywords, making accurate user intent inference and relevant job retrieval particularly challenging. We present dynamic facet suggestion (DFS), an interactive query refinement mechanism that facilitates intent disambiguation by surfacing personalized semantic attributes conditioned on the joint user-query context in real time. We propose a policy-grounded, retrieval-augmented ranking framework for facet suggestion, comprising offline taxonomy curation, embedding-based retrieval of top-K candidates, and distilled small language model (SLM) based candidate scoring. The system is optimized for real-time serving via pointwise single-token scoring with batching and prefix caching. Offline evaluation demonstrates high precision for generated suggestions, and online A/B tests show significant improvements in suggestion engagement and job search outcomes.