AI 中文总结
研究针对生成式检索在推荐和广告系统中的问题，提出EGR框架，利用共享语言模型在同一嵌入空间学习项目与用户表示，经联合对比训练，在多场景评估中表现出色，提升了转化率，简化了系统设计。
AI 中文摘要
生成式检索在大规模推荐和广告系统中越来越受欢迎，但当前方法存在实际复杂性。语义ID方法依赖量化、可变标识符词汇表和令牌到项目的基础；基于嵌入的管道分别训练项目编码器和查询生成器，限制了用户与项目的对齐。我们提出EGR，一种用于推荐和广告的嵌入原生生成式检索框架。EGR使用单个共享语言模型在一个嵌入空间中从项目元数据学习项目表示，并从交互历史学习用户表示。项目直接作为密集向量索引，用户历史编码为密集检索查询。联合对比训练对相关项目进行分组，并使查询与其目标项目对齐。我们在公共基准、工业数据和实时部署上评估EGR。EGR在亚马逊评论上优于已发表的基线；在Snap DPA上，它随数据扩展，处理冷启动项目，并受益于多模态输入。在生产中，EGR提高了2.91%的转化率，简化了系统设计同时提高了检索质量和广告性能。
英文摘要
Generative retrieval is increasingly popular in large-scale recommendation and advertising systems, yet current methods introduce practical complications. Semantic-ID methods rely on quantization, mutable identifier vocabularies, and token-to-item grounding; embedding-based pipelines train the item encoder separately from the query generator, which limits user-item alignment. We propose EGR, an Embedding-Native Generative Retrieval framework for recommendation and advertising. EGR uses a single shared LLM to learn item representations from item metadata and user representations from interaction histories in one embedding space. Items are indexed directly as dense vectors, and user histories are encoded as dense retrieval queries. Joint contrastive training groups related items and aligns queries with their target items. We evaluate EGR on public benchmarks, industrial data, and live deployment. EGR outperforms published baselines on Amazon Reviews; on Snap DPA, it scales with data, handles cold-start items, and benefits from multimodal input. In production, EGR delivers a +2.91% conversion-rate lift, simplifying system design while improving retrieval quality and ad performance.
CommentsAccepted to RecSys 2026
