OptST：优化 LLM 增强推荐的语义分词
原标题：OptST: Optimizing Semantic Tokenization for LLM-Enhanced Recommendation
AI 摘要
论文提出 OptST 方法，用于优化 LLM 增强推荐系统中的语义分词。传统两阶段流程中，分词器先训练、其离散 token 分配在推荐训练时被固定，导致下游推荐器无法修正语义划分。OptST 通过低秩形变并配合锚点正则约束，借助直通估计器将推荐监督信号传回分词器，同时保持硬最近码分配，并按交互选择前缀控制语义分辨率。在四个公开数据集上，OptST 的 AUC 优于传统与 LLM 增强基线，且改进在不同推荐骨干上持续存在。
正文节选
OptST: Optimizing Semantic Tokenization for LLM-Enhanced Recommendation Abstract. Semantic information can enrich the identifiers and structured fields used by recommender systems. Semantic tokenization provides a structured representation of this information by converting LLM-derived user profiles into discrete tokens. In the common two-stage pipeline, the tokenizer is trained before the recommender. Its token assignments are then treated as fixed input features during recommendation training.