HiGenTrans：用分层 LLM 知识迁移改进生成式推荐
HiGenTrans: Hierarchical LLM Knowledge Transfer for Generative Recommendation
这篇论文把 LLM 知识在三个层级迁移进生成式推荐，Recall@10 提了最多 12.9%，做推荐系统的人可以看看实现思路。
arXiv 论文提出 HiGenTrans，一个在输入、表示、决策三层引入 LLM 知识的生成式推荐框架。Global Semantic Priming 在序列开头注入 LLM 用户表示作为语义先验，Hierarchical Representation Transfer 通过均值中心化投影和门控残差对齐中间 LLM 表示，Multi-Signal Decision Calibration 用轻量 MoE 校准器重排 beam-search 结果。在三个公开基准上，HiGenTrans 相比最强基线 Recall@10 最高提升 12.9%，NDCG@10 最高提升 33.7%。语义特征仅基于可观测交互前缀计算，避免目标泄漏且可离线缓存。
HiGenTrans: Hierarchical LLM Knowledge Transfer for Generative Recommendation
Generative recommendation promises to simplify conventional multi-stage recommender systems by generating item Semantic IDs (SIDs) autoregressively. However, two obstacles limit its effective- ness in industrial settings: interaction-only supervision underuses the semantic knowledge encoded in pretrained language models, while beam-search likelihood ranks token sequences rather than directly estimating item relevance. To address these limitations, we propose HiGenTrans, a three-level framework that introduces LLM knowledge at the input, representation, and decision levels. First, Global Semantic Priming (GSP) adds an LLM-derived user representation to the beginning-of-sequence embedding, provid- ing a semantic prior before SID generation. Second, Hierarchi- cal Representation Transfer (HRT) aligns intermediate LLM representations with depth-matched GenRec layers through mean- centered projections and gated residual connections. Finally, Multi- Signal Decision Calibration (MDC) uses a lightweight mixture- of-experts calibrator to combine semantic relevance, generation confidence, and candidate-set context when reranking beam-search outputs. All semantic features are computed only from the observ- able interaction prefix, preventing target leakage, and can be cached offline. Experiments on three public benchmarks show that HiGen- Trans improves Recall@10 by up to 12.9% and NDCG@10 by up to 33.7% over the strongest baselines. These results demonstrate the value of transferring LLM knowledge at complementary stages of the generative recommendation pipeline.