用轻量生成器+离线大模型判断，让推荐更懂用户意图且不伤业务收益。
S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage
- 离线用大模型生成语义评分，线上用轻量模型实时推荐。
- 在线实验提升1.19%商品交易额，点击率显著增长。
- 适合需要兼顾用户偏好和商业目标的工业级推荐系统。
生成式推荐模型通过序列生成直接输出物品，但仅依赖行为日志训练时，对用户真实意图的监督较弱。虽然大语言模型（LLM）能提供丰富的语义先验，但在工业场景中存在两大障碍：语义信号可能与平台商业目标冲突，且大规模推理成本过高。本文提出S-GRec，一个解耦在线轻量生成器与离线LLM语义判官的框架，用于训练阶段的语义监督。S-GRec引入两阶段个性化语义判官（PSJ），从成对反馈中学习用户相关的聚合策略，生成可解释的方面证据，获得稳定语义奖励。为避免语义监督偏离业务目标，采用非对称优势策略优化（A2PO），以业务奖励（如eCPM）为锚点，仅在语义优势与业务一致时注入。在公开基准和大规模生产系统上的实验验证了其有效性与可扩展性，线上A/B测试显示点击率显著提升，商品交易额（GMV）提升1.19%，且无需实时调用大模型。
原文摘要 · Abstract (English)
Generative recommendation models sequence generation to produce items end-to-end, but training from behavioral logs often provides weak supervision on underlying user intent. Although Large Language Models (LLMs) offer rich semantic priors that could supply such supervision, direct adoption in industrial recommendation is hindered by two obstacles: semantic signals can conflict with platform business objectives, and LLM inference is prohibitively expensive at scale. This paper presents S-GRec, a semantic-aware framework that decouples an online lightweight generator from an offline LLM-based semantic judge for train-time supervision. S-GRec introduces a two-stage Personalized Semantic Judge (PSJ) that produces interpretable aspect evidence and learns user-conditional aggregation from pairwise feedback, yielding stable semantic rewards. To prevent semantic supervision from deviating from business goals, Asymmetric Advantage Policy Optimization (A2PO) anchors optimization on business rewards (e.g., eCPM) and injects semantic advantages only when they are consistent. Extensive experiments on public benchmarks and a large-scale production system validate both effectiveness and scalability, including statistically significant gains in CTR and a 1.19\% lift in GMV in online A/B tests, without requiring real-time LLM inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。