基于LLM的用户-商品相关性评估用于动态商品广告
原标题：LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising
AI 摘要
该论文提出一种面向动态商品广告（DPA）检索系统的离线评估指标，用LLM作为语义相关性评判器，对用户-商品相关性进行打分。方法通过Semantic-ID分组、事件分层压缩用户历史为意图代表，并采用智能体式提示框架生成多类别相关性准则，再将教师模型判断蒸馏到高效学生模型以实现规模化评估。实验表明该指标与离线及在线业务指标强相关，可在A/B测试前更快、更可靠地迭代DPA检索系统。
正文节选
LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising Abstract. Dynamic Product Advertising (DPA) retrieval systems are a core component of modern e-commerce advertising; however, their evaluation remains challenging. Conventional offline engagement metrics are limited by sparse, biased feedback, while online evaluation is costly and time-consuming. In this work, we propose a user–product relevance metric for offline evaluation of DPA retrieval systems. The metric first com