研究人员开发了GenAIR，一个旨在通过创建更有效的物品表示来改进序列推荐系统的新框架。该方法使用大型语言模型为每个物品推断一个“原型”，代表其理想的目标受众，然后通过校准目标将其置于实际用户行为中。实验表明，GenAIR在多个数据集上显著提高了各种推荐模型的性能，优于现有方法。 AI
影响 GenAIR的方法可以通过更好地理解物品对特定用户原型的吸引力，从而实现更个性化和更准确的推荐。
排序理由 该集群包含一篇详细介绍序列推荐系统新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.11023v1 Announce Type: cross Abstract: Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large langu…
Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models (LLMs) can provide rich semantic repres…
Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models (LLMs) can provide rich semantic repres…