UniRec: A Unified Expressive-Aligned Generative Recommendation Framework for E-commerce

Abstract

Traditional discriminative recommendation pipelines suffer from objective misalignment and error propagation across stages, motivating a shift toward generative recommendation (GR). However, existing GR methods decode over compact Semantic ID (SID) tokens without access to item-side features, lacking the explicit user–item feature crossing that discriminative models rely on. Combined with the inherent one-to-many nature of recommendation, this absence of item-side signals significantly amplifies generation uncertainty, making the generative paradigm widely regarded as having a lower performance ceiling than its discriminative counterpart. We propose UniRec, a unified expressive-aligned GR framework that unifies the multi-stage pipeline into a single generative model and aligns its expressive power with the discriminative counterpart. Under a fixed-user ranking context with an approximately uniform candidate prior, Bayes’ theorem indicates that the practical gap stems from feature coverage rather than modeling asymmetry, motivating Chain-of-Attribute (CoA)—an expressive-alignment mechanism that pre-generates item attributes before decoding SIDs, recovering item-side feature crossing and yielding measurable per-step entropy reduction. Beyond CoA, Capacity-constrained SID enforces exposure-weighted load balancing to suppress token collapse, and Conditional Decoding Context (CDC) injects scenario-conditioned signals to stabilize multi-scenario decoding and Cartesian-product-based structured summaries of generated tokens to reinforce conditional dependence across decoding layers. A joint Reward-Driven Fine-tuning (RFT) and Direct Preference Optimization (DPO) framework further aligns the model with business objectives. Deployed on a large-scale e-commerce platform, online A/B tests confirm significant gains in page-view click-through rate (PVCTR, +5.37%), orders (+4.76%), and gross merchandise value (GMV, +5.60%).