揭开隐式推理如何激活大模型预训练知识，为生成式推荐注入新思路。
arXiv:2606.14142v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR…
用生成式原型增强项目表示，解决序列推荐中静态编码局限，提升预测精度。
arXiv:2606.11023v1 Announce Type: cross Abstract: Sequential recommendation aims to predict users' next interaction with items by analyzing their hist…
揭秘嵌入技术如何让LLM实现语义理解与精准分类
Article URL: https://matthew-johnston.com/embeddings-llm-best-kept-secret/ Comments URL: https://news.ycombinator.com/item?id=48308035 Points: 2 # Com…
探讨词义表示作为可诱导接口的新视角，为消歧、引导与跨语言对齐提供理论支撑。
arXiv:2605.28669v1 Announce Type: cross Abstract: Sense representations (explicit, per-token meaning decompositions) are useful for disambiguation, st…