研究人员推出 OneReason，一个旨在增强生成推荐模型推理能力的新框架。现有的模型，如 OneRec 系列，由于难以创建有意义的仅包含物品的“思维链”（Chain-of-Thought）序列，因此在激活推理方面存在困难。OneReason 通过关注两个关键因素来解决这个问题：感知（perception），将物品标记（item tokens）与其语义含义联系起来；以及认知（cognition），将用户行为重组为兴趣点。该框架结合了改进的预训练、一种新颖的认知增强型 CoT 格式以及一种专门的训练方法来提升推理能力。 AI
影响 通过提高生成推荐模型的推理能力来增强它们，有可能在各种平台上提供更相关和个性化的推荐。
排序理由 该集群包含一份技术报告，详细介绍了用于生成推荐模型的新研究框架。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.06260v1 Announce Type: cross Abstract: Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from …
Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning abili…