SMART：用于动态产品广告的大语言模型增强混合检索
SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads
浏览论文内容
中文总结 AI 辅助
研究动态产品广告中重定向和开拓新客户的平衡问题，提出SMART方法，通过规则与LLM生成查询结合及质量门控管理成本，经实验验证，该方法有效提升广告转化率，降低LLM成本。
中文摘要 AI 辅助
动态产品广告（DPA）需要从数百万的产品目录中检索相关商品，平衡重定向（重新展现已知兴趣）和开拓新客户（发现新类别）这两个相互竞争的目标。虽然大语言模型（LLM）比传统嵌入模型能更好地捕捉语义意图，但大规模部署会带来高昂的推理成本和词汇不匹配问题。通过对数百万用户的控制实验，我们证明了一种关键的检索分解：规则生成的查询在基于词汇的BM25索引上进行重定向时表现出色，而LLM生成的查询在密集的ANN索引上进行开拓新客户时表现出色。在此基础上，我们提出了SMART（语义感知自适应检索）。为了管理成本，一个轻量级的质量门会识别初始关键词结果中的覆盖差距，仅将约10%从语义开拓新客户中受益的用户自适应地路由到LLM路径。离线评估表明，这种门控方法在相关性得分方面捕获了大部分语义开拓新客户的收益，同时在将LLM成本降低90%的情况下保持了有竞争力的重定向性能。最后，在Snap进行的为期两周的在线A/B测试中，SMART比基于强大嵌入的基线提高了27.6%的广告转化率。
英文摘要
Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories). While Large Language Models (LLMs) capture semantic intent better than traditional embedding models, deploying them at scale introduces prohibitive inference costs and lexical mismatch issues. Through controlled experiments on millions of users, we demonstrate a critical retrieval decomposition: rule-generated queries excel at retargeting on a lexical BM25 index, while LLM-generated queries excel at prospecting on a dense ANN index. Building on this, we propose SMART (SeMantic-aware Adaptive ReTrieval). To manage costs, a lightweight quality gate identifies coverage gaps in initial keyword results, adaptively routing only the ~10% of users who benefit from semantic prospecting to the LLM path. Offline evaluation demonstrates that this gated approach captures the bulk of semantic prospecting gains in Relevance Score while maintaining competitive re-targeting performance at a 90% reduction in LLM costs. Finally, in a 2-week online A/B test at Snap, SMART improved the ad conversion rate by +27.6% over a strong embedding-based baseline.
发表机构
- Snap Inc.（Snap公司）
机构由 AI 辅助整理，请以论文原文为准。
