AI 中文总结
研究针对个性化推荐中货架生成问题，提出内容假设驱动型系统，含假设生成等四个阶段，解耦货架规划与目录填充，支持独立优化，经生产管道结合多种操作，通过离线和在线评估，该系统能扩展个性化推荐供应，效果有竞争力。
AI 中文摘要
现代推荐界面将内容组织成货架，如“更多你喜欢的”或“为你推荐的新发布”等主题行。在生产系统中，这些货架通常通过手工制作的模板和专用检索逻辑来定义。虽然这种方法对广泛的推荐意图有效，但不适用于个人口味的长尾部分。我们提出了一个用于Spotify Home的内容假设驱动型货架生成系统，用描述个性化货架应包含内容的自然语言假设取代固定模板。该系统有四个阶段：假设生成、目录填充、货架对齐和离线服务。这种分解将货架规划与目录填充解耦，支持规划和检索的独立优化，并能对目录实体进行受限生成式检索，还能将前沿语言模型行为提炼成紧凑模型。我们的生产管道结合了假设生成、生成式检索、候选选择和货架对齐、离线语言模型作为评判的评估以及预计算服务。我们描述了端到端架构，并通过离线分析和在Spotify Home上的均匀随机曝光下的早期在线评估对其进行评估。结果表明，假设驱动型货架大幅扩展了个性化推荐供应，其参与度因内容类型而异，在某些情况下与现有的强大货架具有竞争力。
英文摘要
Modern recommendation interfaces organise content into shelves: themed rows such as "More of What You Like" or "New Releases for You." In production systems, these shelves are typically defined through hand-crafted templates coupled with dedicated retrieval logic. While effective for broad recommendation intents, this approach does not scale to the long tail of individual taste. We present a content-hypothesis-driven shelf generation system for Spotify Home that replaces fixed templates with natural-language hypotheses describing what a personalised shelf should contain. The system has four stages hypothesis generation, catalogue fulfilment, shelf alignment, and offline serving. This decomposition decouples shelf planning from catalogue fulfilment, supports independent optimisation of planning and retrieval, and enables both constrained generative retrieval over catalogue entities and distillation of frontier LLM behaviour into compact models. Our production pipeline combines hypothesis generation, generative retrieval, candidate selection and shelf alignment, offline LLM-as-a-judge evaluation, and precomputed serving. We describe the end-to-end architecture and evaluate it through offline analyses and an early online evaluation under uniform random exposure on Spotify Home. Results show that hypothesis-driven shelves substantially expand personalised recommendation supply with engagement that varies by content type and is competitive with strong existing shelves in some settings.
CommentsAccepted at ACM RecSys '26 (Industry Track)
