用属性链提升生成式推荐的表达能力，让推荐更准更稳定。
UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute
- 引入属性链机制，在解码前注入类别、品牌等结构化属性信息。
- 线上实验显示点击率提升5.37%，订单量增4.76%，总成交额增5.60%。
- 适合追求高精度推荐与业务指标优化的电商系统应用。
生成式推荐将检索与排序重构为对语义ID（SID）的自回归解码，统一多阶段流程。但其表达能力仍弱于判别式模型：前者缺乏直接的物品特征访问，无法显式建模用户-物品交叉。我们通过贝叶斯定理证明，若生成模型具备完整特征访问能力，则可等价于判别模型，实际差距源于特征覆盖不全。为此提出UniRec，核心为属性链（CoA）：在每个SID序列前加入类别、卖家、品牌等结构化属性标记，恢复物品侧特征交叉。由于共享相同属性的物品在SID空间中聚集，属性条件化使每步解码熵降低（H(s_k|s<k,a) < H(s_k|s<k)），缩小搜索空间并稳定束搜索。针对部署挑战，提出容量受限下的曝光加权惩罚抑制令牌坍塌；条件解码上下文（CDC）结合任务引导起始符与哈希内容摘要，每步注入场景信号。联合RFT与DPO框架对齐业务目标。实验表明，UniRec在整体上比最强基线高22.6%的HR@50，高价值订单上提升15.5%。在Shopee平台上线后，A/B测试验证点击率提升5.37%，订单量增4.76%，GMV增5.60%。
原文摘要 · Abstract (English)
Generative Recommendation (GR) reframes retrieval and ranking as autoregressive decoding over Semantic IDs (SIDs), unifying the multi-stage pipeline into a single model. Yet a fundamental expressive gap persists: discriminative models score items with direct feature access enabling explicit user-item crossing, whereas GR decodes over compact SID tokens without item-side signal. We formalize this via Bayes' theorem: ranking by p(y|f,u) is equivalent to ranking by p(f|y,u), which factorizes autoregressively over item features, showing that a generative model with full feature access matches its discriminative counterpart, with any practical gap stemming solely from incomplete feature coverage. We propose UniRec with Chain-of-Attribute (CoA) as its core mechanism. CoA prefixes each SID sequence with structured attribute tokens:category, seller, brand, before decoding the SID, recovering the item-side feature crossing that discriminative models exploit. Since items sharing identical attributes cluster in adjacent SID regions, attribute conditioning yields a measurable per-step entropy reduction H(s_k|s<k,a) < H(s_k|s<k), narrowing the search space and stabilizing beam search. We further address two deployment challenges: Capacity-constrained SID introduces exposure-weighted capacity penalties into residual quantization to suppress token collapse and the Matthew effect; Conditional Decoding Context (CDC) combines Task-Conditioned BOS with hash-based Content Summaries to inject scenario signals at each decoding step. A joint RFT and DPO framework aligns the model with business objectives beyond distribution matching. Experiments show UniRec outperforms the strongest baseline by +22.6% HR@50 overall and +15.5% on high-value orders. Deployed on Shopee's e-commerce platform, online A/B tests confirm significant gains in PVCTR (+5.37%), orders (+4.76%), and GMV (+5.60%).
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。