# TSGR: Taobao Search Generative Retrieval

arXiv: https://arxiv.org/abs/2607.18796 · HTML: https://mlsanity.com/paper/2607.18796/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2026.

## Built on by (most cited first, 1 of 1)

- [PailitaoGR: Latent Think-with-Images for Generative Image Retrieval](https://mlsanity.com/paper/2608.26658/) (2026)

## Abstract (arXiv)

Generative retrieval (GR) has demonstrated strong promise for industrial e-commerce search by training a single autoregressive model to directly generate the Semantic IDs (SIDs) of target items. However, existing GR systems are primarily optimized for semantic matching and remain insensitive to item business value: SID construction is value-unaware, and candidates are ranked without access to item side-info. Consequently, high-value items are often missed or deprioritized at the retrieval stage, limiting downstream business impact. This limitation is particularly critical in industrial settings such as Taobao Search, where business objectives are central to system design. To address this, we propose Taobao Search Generative Retrieval (TSGR), a unified generative retrieval framework that incorporates value awareness into both item representation and candidate ranking. 1) For item representation, TSGR introduces Query-aware Parallel SID (QP-SID), which encodes query-conditioned value orderings into the SID construction by building parallel codebooks derived from query-item statistics, so that higher-value and query-relevant items are assigned better token indices. 2) For candidate ranking, we introduce a Value-aware Ranking Module (VRM) that is built upon and jointly optimized with the GR, enabling a single model to seamlessly serve as both retriever and pre-ranker without a dedicated pre-ranking stage. A progressive training pipeline further aligns the model with semantic relevance, user preferences, and business objectives. Offline experiments show that TSGR achieves a 9.16% improvement in HR@1000, and online A/B tests further validate its effectiveness, yielding gains of +0.43% in IPV, +1.12% in Transaction Count, and +1.64% in GMV. TSGR has been fully deployed in production.