针对求职者短关键词搜索，动态推荐精准筛选项提升匹配效果
Policy-Grounded Dynamic Facet Suggestions for Job Search
- 基于用户查询上下文实时生成个性化筛选建议
- 在线测试显示点击率与求职结果显著提升
- 适合优化招聘平台搜索体验的工程师和产品经理
求职者常使用简短、不明确的关键词发起搜索。在领英平台上，超过80%的求职相关查询包含三个或更少的关键词，导致用户意图识别和职位精准召回面临巨大挑战。本文提出动态筛选建议（DFS），一种交互式查询优化机制，通过实时呈现基于用户-查询联合上下文的个性化语义属性，辅助意图消歧。我们设计了一种策略驱动的检索增强排序框架，包含离线知识图谱构建、基于嵌入的候选检索（前K个）以及由小型语言模型（SLM）进行的候选打分。系统通过单标记点式评分、批处理和前缀缓存实现低延迟实时服务。离线评估显示建议准确率高，线上A/B测试表明建议点击率与求职转化效果显著提升。
原文摘要 · Abstract (English)
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.
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。