UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute

TL;DR

UniRec introduces Chain-of-Attribute to bridge the gap between generative and discriminative recommendation models, improving ranking accuracy and deployment stability in e-commerce.

Contribution

The paper proposes UniRec with Chain-of-Attribute, a novel mechanism that incorporates structured attribute tokens to enhance generative recommendation models.

Findings

UniRec outperforms baselines by +22.6% HR@50 overall.

Online A/B tests show +5.37% PVCTR, +4.76% orders, +5.60% GMV.

Attribute conditioning reduces search space and stabilizes beam search.

Abstract

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%).