12 papers
TSGR: Taobao Search Generative Retrieval
Tianyu Zhan, Gui Ling, Tong Xiong +9
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…
Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval
Gui Ling, Zhihong Chen, Yu Li +7
The paper proposes Cluster‑Ranked Identifier (CRID), a document ID design that separates semantic clustering from business‑value ranking to eliminate collisions and better align re…
Prompt Generation Technical Report
Dan Ou, Gui Ling, Hao Wan +25
The paper introduces Prompt Generation (PG), a configuration‑driven framework that separates feature processing from model architecture for generative retrieval systems, enabling f…
TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
Jianhui Yang, Yiming Jin, Pengkun Jiao +6
Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex…
UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking
Liren Yu, Caiyuan Li, Feiyi Dong +5
Recent advances in Large Language Models (LLMs) have inspired a surge of scaling research in industrial search, advertising, and recommendation systems. However, existing approache…
SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance
Pengkun Jiao, Yiming Jin, Jianhui Yang +6
Query-product relevance prediction is vital for AI-driven e-commerce, yet current LLM-based approaches face a dilemma: SFT and DPO struggle with long-tail generalization due to coa…