语义ID：联合生成式搜索与推荐

摘要

由大型语言模型（LLMs）驱动的生成模型正逐渐成为推荐与搜索任务的一体化解决方案。这些模型中的一个关键设计选择是如何表示物品，传统上通过唯一标识符（IDs），而近期则采用由嵌入获得的离散代码构成的语义ID。尽管针对特定任务的嵌入模型能提升单个任务的性能，但在联合场景下可能泛化不佳。本文探讨了在使用统一模型时，如何构建在搜索与推荐中均表现优异的语义ID。我们比较了多种构建语义ID的策略，包括任务专用与跨任务方法，以及在联合搜索与推荐生成模型中，是否应为每项任务分配独立的语义ID标记。研究结果表明，采用在搜索与推荐任务上均经过微调的双编码器模型获取物品嵌入，随后构建统一的语义ID空间，能够实现有效的权衡，使两项任务均展现出强劲性能。我们期望这些发现能激发后续关于可泛化、基于语义的ID方案的研究，并为下一代一体化生成式推荐架构提供指导。

English

Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models is how to represent items, traditionally through unique identifiers (IDs) and more recently with Semantic IDs composed of discrete codes, obtained from embeddings. While task-specific embedding models can improve performance for individual tasks, they may not generalize well in a joint setting. In this paper, we explore how to construct Semantic IDs that perform well both in search and recommendation when using a unified model. We compare a range of strategies to construct Semantic IDs, looking into task-specific and cross-tasks approaches, and also whether each task should have its own semantic ID tokens in a joint search and recommendation generative model. Our results show that using a bi-encoder model fine-tuned on both search and recommendation tasks to obtain item embeddings, followed by the construction of a unified Semantic ID space provides an effective trade-off, enabling strong performance in both tasks. We hope these findings spark follow-up work on generalisable, semantically grounded ID schemes and inform the next wave of unified generative recommender architectures.

语义ID：联合生成式搜索与推荐

Semantic IDs for Joint Generative Search and Recommendation

摘要

Support